20220823.md

ArXiv cs.CV --Tue, 23 Aug 2022

1.SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration ⬇️

Next Best View computation (NBV) is a long-standing problem in robotics, and consists in identifying the next most informative sensor position(s) for reconstructing a 3D object or scene efficiently and accurately. Like most current methods, we consider NBV prediction from a depth sensor. Learning-based methods relying on a volumetric representation of the scene are suitable for path planning, but do not scale well with the size of the scene and have lower accuracy than methods using a surface-based representation. However, the latter constrain the camera to a small number of poses. To obtain the advantages of both representations, we show that we can maximize surface metrics by Monte Carlo integration over a volumetric representation. Our method scales to large scenes and handles free camera motion: It takes as input an arbitrarily large point cloud gathered by a depth sensor like Lidar systems as well as camera poses to predict NBV. We demonstrate our approach on a novel dataset made of large and complex 3D scenes.

2.Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks ⬇️

A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).

3.ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition ⬇️

Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up studies due to its self-explanatory property for explainable artificial intelligence (XAI). However, when directly applying ProtoPNet on vision transformer (ViT) backbones, learned prototypes have a ''distraction'' problem: they have a relatively high probability of being activated by the background and pay less attention to the foreground. The powerful capability of modeling long-term dependency makes the transformer-based ProtoPNet hard to focus on prototypical parts, thus severely impairing its inherent interpretability. This paper proposes prototypical part transformer (ProtoPFormer) for appropriately and effectively applying the prototype-based method with ViTs for interpretable image recognition. The proposed method introduces global and local prototypes for capturing and highlighting the representative holistic and partial features of targets according to the architectural characteristics of ViTs. The global prototypes are adopted to provide the global view of objects to guide local prototypes to concentrate on the foreground while eliminating the influence of the background. Afterwards, local prototypes are explicitly supervised to concentrate on their respective prototypical visual parts, increasing the overall interpretability. Extensive experiments demonstrate that our proposed global and local prototypes can mutually correct each other and jointly make final decisions, which faithfully and transparently reason the decision-making processes associatively from the whole and local perspectives, respectively. Moreover, ProtoPFormer consistently achieves superior performance and visualization results over the state-of-the-art (SOTA) prototype-based baselines. Our code has been released at this https URL.

4.Patient-level Microsatellite Stability Assessment from Whole Slide Images By Combining Momentum Contrast Learning and Group Patch Embeddings ⬇️

Assessing microsatellite stability status of a patient's colorectal cancer is crucial in personalizing treatment regime. Recently, convolutional-neural-networks (CNN) combined with transfer-learning approaches were proposed to circumvent traditional laboratory testing for determining microsatellite status from hematoxylin and eosin stained biopsy whole slide images (WSI). However, the high resolution of WSI practically prevent direct classification of the entire WSI. Current approaches bypass the WSI high resolution by first classifying small patches extracted from the WSI, and then aggregating patch-level classification logits to deduce the patient-level status. Such approaches limit the capacity to capture important information which resides at the high resolution WSI data. We introduce an effective approach to leverage WSI high resolution information by momentum contrastive learning of patch embeddings along with training a patient-level classifier on groups of those embeddings. Our approach achieves up to 7.4% better accuracy compared to the straightforward patch-level classification and patient level aggregation approach with a higher stability (AUC, $0.91 \pm 0.01$ vs. $0.85 \pm 0.04$, p-value$<0.01$). Our code can be found at this https URL.

5.FurryGAN: High Quality Foreground-aware Image Synthesis ⬇️

Foreground-aware image synthesis aims to generate images as well as their foreground masks. A common approach is to formulate an image as an masked blending of a foreground image and a background image. It is a challenging problem because it is prone to reach the trivial solution where either image overwhelms the other, i.e., the masks become completely full or empty, and the foreground and background are not meaningfully separated. We present FurryGAN with three key components: 1) imposing both the foreground image and the composite image to be realistic, 2) designing a mask as a combination of coarse and fine masks, and 3) guiding the generator by an auxiliary mask predictor in the discriminator. Our method produces realistic images with remarkably detailed alpha masks which cover hair, fur, and whiskers in a fully unsupervised manner.

6.MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation ⬇️

Avatar refers to a representative of a physical user in the virtual world that can engage in different activities and interact with other objects in metaverse. Simulating the avatar requires accurate human pose estimation. Though camera-based solutions yield remarkable performance, they encounter the privacy issue and degraded performance caused by varying illumination, especially in smart home. In this paper, we propose a WiFi-based IoT-enabled human pose estimation scheme for metaverse avatar simulation, namely MetaFi. Specifically, a deep neural network is designed with customized convolutional layers and residual blocks to map the channel state information to human pose landmarks. It is enforced to learn the annotations from the accurate computer vision model, thus achieving cross-modal supervision. WiFi is ubiquitous and robust to illumination, making it a feasible solution for avatar applications in smart home. The experiments are conducted in the real world, and the results show that the MetaFi achieves very high performance with a PCK@50 of 95.23%.

7.Minimizing the Effect of Noise and Limited Dataset Size in Image Classification Using Depth Estimation as an Auxiliary Task with Deep Multitask Learning ⬇️

Generalizability is the ultimate goal of Machine Learning (ML) image classifiers, for which noise and limited dataset size are among the major concerns. We tackle these challenges through utilizing the framework of deep Multitask Learning (dMTL) and incorporating image depth estimation as an auxiliary task. On a customized and depth-augmented derivation of the MNIST dataset, we show a) multitask loss functions are the most effective approach of implementing dMTL, b) limited dataset size primarily contributes to classification inaccuracy, and c) depth estimation is mostly impacted by noise. In order to further validate the results, we manually labeled the NYU Depth V2 dataset for scene classification tasks. As a contribution to the field, we have made the data in python native format publicly available as an open-source dataset and provided the scene labels. Our experiments on MNIST and NYU-Depth-V2 show dMTL improves generalizability of the classifiers when the dataset is noisy and the number of examples is limited.

8.Fight Fire With Fire: Reversing Skin Adversarial Examples by Multiscale Diffusive and Denoising Aggregation Mechanism ⬇️

Reliable skin cancer diagnosis models play an essential role in early screening and medical intervention. Prevailing computer-aided skin cancer classification systems employ deep learning approaches. However, recent studies reveal their extreme vulnerability to adversarial attacks -- often imperceptible perturbations to significantly reduce performances of skin cancer diagnosis models. To mitigate these threats, this work presents a simple, effective and resource-efficient defense framework by reverse engineering adversarial perturbations in skin cancer images. Specifically, a multiscale image pyramid is first established to better preserve discriminative structures in medical imaging domain. To neutralize adversarial effects, skin images at different scales are then progressively diffused by injecting isotropic Gaussian noises to move the adversarial examples to the clean image manifold. Crucially, to further reverse adversarial noises and suppress redundant injected noises, a novel multiscale denoising mechanism is carefully designed that aggregates image information from neighboring scales. We evaluated the defensive effectiveness of our method on ISIC 2019, a largest skin cancer multiclass classification dataset. Experimental results demonstrate that the proposed method can successfully reverse adversarial perturbations from different attacks and significantly outperform some state-of-the-art methods in defending skin cancer diagnosis models.

9.Collaborative Perception for Autonomous Driving: Current Status and Future Trend ⬇️

Perception is one of the crucial module of the autonomous driving system, which has made great progress recently. However, limited ability of individual vehicles results in the bottleneck of improvement of the perception performance. To break through the limits of individual perception, collaborative perception has been proposed which enables vehicles to share information to perceive the environments beyond line-of-sight and field-of-view. In this paper, we provide a review of the related work about the promising collaborative perception technology, including introducing the fundamental concepts, generalizing the collaboration modes and summarizing the key ingredients and applications of collaborative perception. Finally, we discuss the open challenges and issues of this research area and give some potential further directions.

10.A Medical Semantic-Assisted Transformer for Radiographic Report Generation ⬇️

Automated radiographic report generation is a challenging cross-domain task that aims to automatically generate accurate and semantic-coherence reports to describe medical images. Despite the recent progress in this field, there are still many challenges at least in the following aspects. First, radiographic images are very similar to each other, and thus it is difficult to capture the fine-grained visual differences using CNN as the visual feature extractor like many existing methods. Further, semantic information has been widely applied to boost the performance of generation tasks (e.g. image captioning), but existing methods often fail to provide effective medical semantic features. Toward solving those problems, in this paper, we propose a memory-augmented sparse attention block utilizing bilinear pooling to capture the higher-order interactions between the input fine-grained image features while producing sparse attention. Moreover, we introduce a novel Medical Concepts Generation Network (MCGN) to predict fine-grained semantic concepts and incorporate them into the report generation process as guidance. Our proposed method shows promising performance on the recently released largest benchmark MIMIC-CXR. It outperforms multiple state-of-the-art methods in image captioning and medical report generation.

11.Neuro-Symbolic Visual Dialog ⬇️

We propose Neuro-Symbolic Visual Dialog (NSVD) -the first method to combine deep learning and symbolic program execution for multi-round visually-grounded reasoning. NSVD significantly outperforms existing purely-connectionist methods on two key challenges inherent to visual dialog: long-distance co-reference resolution as well as vanishing question-answering performance. We demonstrate the latter by proposing a more realistic and stricter evaluation scheme in which we use predicted answers for the full dialog history when calculating accuracy. We describe two variants of our model and show that using this new scheme, our best model achieves an accuracy of 99.72% on CLEVR-Dialog -a relative improvement of more than 10% over the state of the art while only requiring a fraction of training data. Moreover, we demonstrate that our neuro-symbolic models have a higher mean first failure round, are more robust against incomplete dialog histories, and generalise better not only to dialogs that are up to three times longer than those seen during training but also to unseen question types and scenes.

12.Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild ⬇️

Compared with the image-based static facial expression recognition (SFER) task, the dynamic facial expression recognition (DFER) task based on video sequences is closer to the natural expression recognition scene. However, DFER is often more challenging. One of the main reasons is that video sequences often contain frames with different expression intensities, especially for the facial expressions in the real-world scenarios, while the images in SFER frequently present uniform and high expression intensities. However, if the expressions with different intensities are treated equally, the features learned by the networks will have large intra-class and small inter-class differences, which is harmful to DFER. To tackle this problem, we propose the global convolution-attention block (GCA) to rescale the channels of the feature maps. In addition, we introduce the intensity-aware loss (IAL) in the training process to help the network distinguish the samples with relatively low expression intensities. Experiments on two in-the-wild dynamic facial expression datasets (i.e., DFEW and FERV39k) indicate that our method outperforms the state-of-the-art DFER approaches. The source code will be made publicly available.

13.To show or not to show: Redacting sensitive text from videos of electronic displays ⬇️

With the increasing prevalence of video recordings there is a growing need for tools that can maintain the privacy of those recorded. In this paper, we define an approach for redacting personally identifiable text from videos using a combination of optical character recognition (OCR) and natural language processing (NLP) techniques. We examine the relative performance of this approach when used with different OCR models, specifically Tesseract and the OCR system from Google Cloud Vision (GCV). For the proposed approach the performance of GCV, in both accuracy and speed, is significantly higher than Tesseract. Finally, we explore the advantages and disadvantages of both models in real-world applications.

14.Learning Branched Fusion and Orthogonal Projection for Face-Voice Association ⬇️

Recent years have seen an increased interest in establishing association between faces and voices of celebrities leveraging audio-visual information from YouTube. Prior works adopt metric learning methods to learn an embedding space that is amenable for associated matching and verification tasks. Albeit showing some progress, such formulations are, however, restrictive due to dependency on distance-dependent margin parameter, poor run-time training complexity, and reliance on carefully crafted negative mining procedures. In this work, we hypothesize that an enriched representation coupled with an effective yet efficient supervision is important towards realizing a discriminative joint embedding space for face-voice association tasks. To this end, we propose a light-weight, plug-and-play mechanism that exploits the complementary cues in both modalities to form enriched fused embeddings and clusters them based on their identity labels via orthogonality constraints. We coin our proposed mechanism as fusion and orthogonal projection (FOP) and instantiate in a two-stream network. The overall resulting framework is evaluated on VoxCeleb1 and MAV-Celeb datasets with a multitude of tasks, including cross-modal verification and matching. Results reveal that our method performs favourably against the current state-of-the-art methods and our proposed formulation of supervision is more effective and efficient than the ones employed by the contemporary methods. In addition, we leverage cross-modal verification and matching tasks to analyze the impact of multiple languages on face-voice association. Code is available: \url{this https URL}

15.An anomaly detection approach for backdoored neural networks: face recognition as a case study ⬇️

Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker. Given how stealthy backdoor attacks are, consequences of these backdoors could be disastrous if such networks were to be deployed for applications as critical as border or access control. In this paper, we propose a novel backdoored network detection method based on the principle of anomaly detection, involving access to the clean part of the training data and the trained network. We highlight its promising potential when considering various triggers, locations and identity pairs, without the need to make any assumptions on the nature of the backdoor and its setup. We test our method on a novel dataset of backdoored networks and report detectability results with perfect scores.

16.Dynamic Adaptive Threshold based Learning for Noisy Annotations Robust Facial Expression Recognition ⬇️

The real-world facial expression recognition (FER) datasets suffer from noisy annotations due to crowd-sourcing, ambiguity in expressions, the subjectivity of annotators and inter-class similarity. However, the recent deep networks have strong capacity to memorize the noisy annotations leading to corrupted feature embedding and poor generalization. To handle noisy annotations, we propose a dynamic FER learning framework (DNFER) in which clean samples are selected based on dynamic class specific threshold during training. Specifically, DNFER is based on supervised training using selected clean samples and unsupervised consistent training using all the samples. During training, the mean posterior class probabilities of each mini-batch is used as dynamic class-specific threshold to select the clean samples for supervised training. This threshold is independent of noise rate and does not need any clean data unlike other methods. In addition, to learn from all samples, the posterior distributions between weakly-augmented image and strongly-augmented image are aligned using an unsupervised consistency loss. We demonstrate the robustness of DNFER on both synthetic as well as on real noisy annotated FER datasets like RAFDB, FERPlus, SFEW and AffectNet.

17.PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling ⬇️

Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods rely on pseudo-ground truth to augment the currently limited training data available for learning such models. In this paper, we introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling. It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information. We showcase variants of PoseBERT with different inputs varying from 3D skeleton keypoints to rotations of a 3D parametric model for either the full body (SMPL) or just the hands (MANO). Since PoseBERT training is task agnostic, the model can be applied to several tasks such as pose refinement, future pose prediction or motion completion without finetuning. Our experimental results validate that adding PoseBERT on top of various state-of-the-art pose estimation methods consistently improves their performances, while its low computational cost allows us to use it in a real-time demo for smoothly animating a robotic hand via a webcam. Test code and models are available at this https URL.

18.Aesthetics Driven Autonomous Time-Lapse Photography Generation by Virtual and Real Robots ⬇️

Time-lapse photography is employed in movies and promotional films because it can reflect the passage of time in a short time and strengthen the visual attraction. However, since it takes a long time and requires the stable shooting, it is a great challenge for the photographer.
In this article, we propose a time-lapse photography system with virtual and real robots. To help users shoot time-lapse videos efficiently, we first parameterize the time-lapse photography and propose a parameter optimization method. For different parameters, different aesthetic models, including image and video aesthetic quality assessment networks, are used to generate optimal parameters. Then we propose a time-lapse photography interface to facilitate users to view and adjust parameters and use virtual robots to conduct virtual photography in a three-dimensional scene. The system can also export the parameters and provide them to real robots so that the time-lapse videos can be filmed in the real world.
In addition, we propose a time-lapse photography aesthetic assessment method that can automatically evaluate the aesthetic quality of time-lapse video.
The experimental results show that our method can efficiently obtain the time-lapse videos. We also conduct a user study. The results show that our system has the similar effect as professional photographers and is more efficient.

19.TaCo: Textual Attribute Recognition via Contrastive Learning ⬇️

As textual attributes like font are core design elements of document format and page style, automatic attributes recognition favor comprehensive practical applications. Existing approaches already yield satisfactory performance in differentiating disparate attributes, but they still suffer in distinguishing similar attributes with only subtle difference. Moreover, their performance drop severely in real-world scenarios where unexpected and obvious imaging distortions appear. In this paper, we aim to tackle these problems by proposing TaCo, a contrastive framework for textual attribute recognition tailored toward the most common document scenes. Specifically, TaCo leverages contrastive learning to dispel the ambiguity trap arising from vague and open-ended attributes. To realize this goal, we design the learning paradigm from three perspectives: 1) generating attribute views, 2) extracting subtle but crucial details, and 3) exploiting valued view pairs for learning, to fully unlock the pre-training potential. Extensive experiments show that TaCo surpasses the supervised counterparts and advances the state-of-the-art remarkably on multiple attribute recognition tasks. Online services of TaCo will be made available.

20.Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation ⬇️

Albeit with varying degrees of progress in the field of Semi-Supervised Semantic Segmentation, most of its recent successes are involved in unwieldy models and the lightweight solution is still not yet explored. We find that existing knowledge distillation techniques pay more attention to pixel-level concepts from labeled data, which fails to take more informative cues within unlabeled data into account. Consequently, we offer the first attempt to provide lightweight SSSS models via a novel multi-granularity distillation (MGD) scheme, where multi-granularity is captured from three aspects: i) complementary teacher structure; ii) labeled-unlabeled data cooperative distillation; iii) hierarchical and multi-levels loss setting. Specifically, MGD is formulated as a labeled-unlabeled data cooperative distillation scheme, which helps to take full advantage of diverse data characteristics that are essential in the semi-supervised setting. Image-level semantic-sensitive loss, region-level content-aware loss, and pixel-level consistency loss are set up to enrich hierarchical distillation abstraction via structurally complementary teachers. Experimental results on PASCAL VOC2012 and Cityscapes reveal that MGD can outperform the competitive approaches by a large margin under diverse partition protocols. For example, the performance of ResNet-18 and MobileNet-v2 backbone is boosted by 11.5% and 4.6% respectively under 1/16 partition protocol on Cityscapes. Although the FLOPs of the model backbone is compressed by 3.4-5.3x (ResNet-18) and 38.7-59.6x (MobileNetv2), the model manages to achieve satisfactory segmentation results.

21.Prompt-Matched Semantic Segmentation ⬇️

The objective of this work is to explore how to effectively and efficiently adapt pre-trained foundation models to various downstream tasks of image semantic segmentation. Conventional methods usually fine-tuned the whole networks for each specific dataset and it was burdensome to store the massive parameters of these networks. A few recent works attempted to insert some trainable parameters into the frozen network to learn visual prompts for efficient tuning. However, these works significantly modified the original structure of standard modules, making them inoperable on many existing high-speed inference devices, where standard modules and their parameters have been embedded. To facilitate prompt-based semantic segmentation, we propose a novel Inter-Stage Prompt-Matched Framework, which maintains the original structure of the foundation model while generating visual prompts adaptively for task-oriented tuning. Specifically, the pre-trained model is first divided into multiple stages, and their parameters are frozen and shared for all semantic segmentation tasks. A lightweight module termed Semantic-aware Prompt Matcher is then introduced to hierarchically interpolate between two stages to learn reasonable prompts for each specific task under the guidance of interim semantic maps. In this way, we can better stimulate the pre-trained knowledge of the frozen model to learn semantic concepts effectively on downstream datasets. Extensive experiments conducted on five benchmarks show that the proposed method can achieve a promising trade-off between parameter efficiency and performance effectiveness.

22.Meta-Causal Feature Learning for Out-of-Distribution Generalization ⬇️

Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features. However, conventional methods apply causal learners from multiple data splits, which may incur biased representation learning from imbalanced data distributions and difficulty in invariant feature learning from heterogeneous sources. To address these issues, this paper presents a balanced meta-causal learner (BMCL), which includes a balanced task generation module (BTG) and a meta-causal feature learning module (MCFL). Specifically, the BTG module learns to generate balanced subsets by a self-learned partitioning algorithm with constraints on the proportions of sample classes and contexts. The MCFL module trains a meta-learner adapted to different distributions. Experiments conducted on NICO++ dataset verified that BMCL effectively identifies the class-invariant visual regions for classification and may serve as a general framework to improve the performance of the state-of-the-art methods.

23.STS: Surround-view Temporal Stereo for Multi-view 3D Detection ⬇️

Learning accurate depth is essential to multi-view 3D object detection. Recent approaches mainly learn depth from monocular images, which confront inherent difficulties due to the ill-posed nature of monocular depth learning. Instead of using a sole monocular depth method, in this work, we propose a novel Surround-view Temporal Stereo (STS) technique that leverages the geometry correspondence between frames across time to facilitate accurate depth learning. Specifically, we regard the field of views from all cameras around the ego vehicle as a unified view, namely surroundview, and conduct temporal stereo matching on it. The resulting geometrical correspondence between different frames from STS is utilized and combined with the monocular depth to yield final depth prediction. Comprehensive experiments on nuScenes show that STS greatly boosts 3D detection ability, notably for medium and long distance objects. On BEVDepth with ResNet-50 backbone, STS improves mAP and NDS by 2.6% and 1.4%, respectively. Consistent improvements are observed when using a larger backbone and a larger image resolution, demonstrating its effectiveness

24.Rethinking Knowledge Distillation via Cross-Entropy ⬇️

Knowledge Distillation (KD) has developed extensively and boosted various tasks. The classical KD method adds the KD loss to the original cross-entropy (CE) loss. We try to decompose the KD loss to explore its relation with the CE loss. Surprisingly, we find it can be regarded as a combination of the CE loss and an extra loss which has the identical form as the CE loss. However, we notice the extra loss forces the student's relative probability to learn the teacher's absolute probability. Moreover, the sum of the two probabilities is different, making it hard to optimize. To address this issue, we revise the formulation and propose a distributed loss. In addition, we utilize teachers' target output as the soft target, proposing the soft loss. Combining the soft loss and the distributed loss, we propose a new KD loss (NKD). Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD). Our method achieves state-of-the-art performance on CIFAR-100 and ImageNet. For example, with ResNet-34 as the teacher, we boost the ImageNet Top-1 accuracy of ResNet18 from 69.90% to 71.96%. In training without teachers, MobileNet, ResNet-18 and SwinTransformer-Tiny achieve 70.04%, 70.76%, and 81.48%, which are 0.83%, 0.86%, and 0.30% higher than the baseline, respectively. The code is available at this https URL.

25.SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization ⬇️

Matching-based methods, especially those based on space-time memory, are significantly ahead of other solutions in semi-supervised video object segmentation (VOS). However, continuously growing and redundant template features lead to an inefficient inference. To alleviate this, we propose a novel Sequential Weighted Expectation-Maximization (SWEM) network to greatly reduce the redundancy of memory features. Different from the previous methods which only detect feature redundancy between frames, SWEM merges both intra-frame and inter-frame similar features by leveraging the sequential weighted EM algorithm. Further, adaptive weights for frame features endow SWEM with the flexibility to represent hard samples, improving the discrimination of templates. Besides, the proposed method maintains a fixed number of template features in memory, which ensures the stable inference complexity of the VOS system. Extensive experiments on commonly used DAVIS and YouTube-VOS datasets verify the high efficiency (36 FPS) and high performance (84.3% $\mathcal{J}&amp;amp;\mathcal{F}$ on DAVIS 2017 validation dataset) of SWEM. Code is available at: this https URL.

26.Revising Image-Text Retrieval via Multi-Modal Entailment ⬇️

An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from fitting other images. We observe that such a many-to-many matching phenomenon is quite common in the widely-used retrieval datasets, where one caption can describe up to 178 images. These large matching-lost data not only confuse the model in training but also weaken the evaluation accuracy. Inspired by visual and textual entailment tasks, we propose a multi-modal entailment classifier to determine whether a sentence is entailed by an image plus its linked captions. Subsequently, we revise the image-text retrieval datasets by adding these entailed captions as additional weak labels of an image and develop a universal variable learning rate strategy to teach a retrieval model to distinguish the entailed captions from other negative samples. In experiments, we manually annotate an entailment-corrected image-text retrieval dataset for evaluation. The results demonstrate that the proposed entailment classifier achieves about 78% accuracy and consistently improves the performance of image-text retrieval baselines.

27.Lirot.ai: A Novel Platform for Crowd-Sourcing Retinal Image Segmentations ⬇️

Introduction: For supervised deep learning (DL) tasks, researchers need a large annotated dataset. In medical data science, one of the major limitations to develop DL models is the lack of annotated examples in large quantity. This is most often due to the time and expertise required to annotate. We introduce this http URL, a novel platform for facilitating and crowd-sourcing image segmentations. Methods: this http URL is composed of three components; an iPadOS client application named this http URL-app, a backend server named this http URL-server and a python API name this http URL-API. this http URL-app was developed in Swift 5.6 and this http URL-server is a firebase backend. this http URL-API allows the management of the database. this http URL-app can be installed on as many iPadOS devices as needed so that annotators may be able to perform their segmentation simultaneously and remotely. We incorporate Apple Pencil compatibility, making the segmentation faster, more accurate, and more intuitive for the expert than any other computer-based alternative. Results: We demonstrate the usage of this http URL for the creation of a retinal fundus dataset with reference vasculature segmentations. Discussion and future work: We will use active learning strategies to continue enlarging our retinal fundus dataset by including a more efficient process to select the images to be annotated and distribute them to annotators.

28.Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding ⬇️

There has been an increasing interest in multi-task learning for video understanding in recent years. In this work, we propose a generalized notion of multi-task learning by incorporating both auxiliary tasks that the model should perform well on and adversarial tasks that the model should not perform well on. We employ Necessary Condition Analysis (NCA) as a data-driven approach for deciding what category these tasks should fall in. Our novel proposed framework, Adversarial Multi-Task Neural Networks (AMT), penalizes adversarial tasks, determined by NCA to be scene recognition in the Holistic Video Understanding (HVU) dataset, to improve action recognition. This upends the common assumption that the model should always be encouraged to do well on all tasks in multi-task learning. Simultaneously, AMT still retains all the benefits of multi-task learning as a generalization of existing methods and uses object recognition as an auxiliary task to aid action recognition. We introduce two challenging Scene-Invariant test splits of HVU, where the model is evaluated on action-scene co-occurrences not encountered in training. We show that our approach improves accuracy by ~3% and encourages the model to attend to action features instead of correlation-biasing scene features.

29.Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking ⬇️

Recent research in multi-task learning reveals the benefit of solving related problems in a single neural network. 3D object detection and multi-object tracking (MOT) are two heavily intertwined problems predicting and associating an object instance location across time. However, most previous works in 3D MOT treat the detector as a preceding separated pipeline, disjointly taking the output of the detector as an input to the tracker. In this work, we present Minkowski Tracker, a sparse spatio-temporal R-CNN that jointly solves object detection and tracking. Inspired by region-based CNN (R-CNN), we propose to solve tracking as a second stage of the object detector R-CNN that predicts assignment probability to tracks. First, Minkowski Tracker takes 4D point clouds as input to generate a spatio-temporal Bird's-eye-view (BEV) feature map through a 4D sparse convolutional encoder network. Then, our proposed TrackAlign aggregates the track region-of-interest (ROI) features from the BEV features. Finally, Minkowski Tracker updates the track and its confidence score based on the detection-to-track match probability predicted from the ROI features. We show in large-scale experiments that the overall performance gain of our method is due to four factors: 1. The temporal reasoning of the 4D encoder improves the detection performance 2. The multi-task learning of object detection and MOT jointly enhances each other 3. The detection-to-track match score learns implicit motion model to enhance track assignment 4. The detection-to-track match score improves the quality of the track confidence score. As a result, Minkowski Tracker achieved the state-of-the-art performance on Nuscenes dataset tracking task without hand-designed motion models.

30.Reference-Limited Compositional Zero-Shot Learning ⬇️

Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world. While considerable progress has been made on existing benchmarks, we suspect whether popular CZSL methods can address the challenges of few-shot and few referential compositions, which is common when learning in real-world unseen environments. To this end, we study the challenging reference-limited compositional zero-shot learning (RL-CZSL) problem in this paper, i.e. , given limited seen compositions that contain only a few samples as reference, unseen compositions of observed primitives should be identified. We propose a novel Meta Compositional Graph Learner (MetaCGL) that can efficiently learn the compositionality from insufficient referential information and generalize to unseen compositions. Besides, we build a benchmark with two new large-scale datasets that consist of natural images with diverse compositional labels, providing more realistic environments for RL-CZSL. Extensive experiments in the benchmarks show that our method achieves state-of-the-art performance in recognizing unseen compositions when reference is limited for compositional learning.

31.Multilayer deep feature extraction for visual texture recognition ⬇️

Convolutional neural networks have shown successful results in image classification achieving real-time results superior to the human level. However, texture images still pose some challenge to these models due, for example, to the limited availability of data for training in several problems where these images appear, high inter-class similarity, the absence of a global viewpoint of the object represented, and others. In this context, the present paper is focused on improving the accuracy of convolutional neural networks in texture classification. This is done by extracting features from multiple convolutional layers of a pretrained neural network and aggregating such features using Fisher vector. The reason for using features from earlier convolutional layers is obtaining information that is less domain specific. We verify the effectiveness of our method on texture classification of benchmark datasets, as well as on a practical task of Brazilian plant species identification. In both scenarios, Fisher vectors calculated on multiple layers outperform state-of-art methods, confirming that early convolutional layers provide important information about the texture image for classification.

32.Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning ⬇️

Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little attention has been given to how to quantify the dominance severity of head classes in the representation space. Motivated by this, we generalize the cosine-based classifiers to a von Mises-Fisher (vMF) mixture model, denoted as vMF classifier, which enables to quantitatively measure representation quality upon the hyper-sphere space via calculating distribution overlap coefficient. To our knowledge, this is the first work to measure representation quality of classifiers and features from the perspective of distribution overlap coefficient. On top of it, we formulate the inter-class discrepancy and class-feature consistency loss terms to alleviate the interference among the classifier weights and align features with classifier weights. Furthermore, a novel post-training calibration algorithm is devised to zero-costly boost the performance via inter-class overlap coefficients. Our method outperforms previous work with a large margin and achieves state-of-the-art performance on long-tailed image classification, semantic segmentation, and instance segmentation tasks (e.g., we achieve 55.0% overall accuracy with ResNetXt-50 in ImageNet-LT). Our code is available at this https URL_OP.

33.A Simple Baseline for Multi-Camera 3D Object Detection ⬇️

3D object detection with surrounding cameras has been a promising direction for autonomous driving. In this paper, we present SimMOD, a Simple baseline for Multi-camera Object Detection, to solve the problem. To incorporate multi-view information as well as build upon previous efforts on monocular 3D object detection, the framework is built on sample-wise object proposals and designed to work in a two-stage manner. First, we extract multi-scale features and generate the perspective object proposals on each monocular image. Second, the multi-view proposals are aggregated and then iteratively refined with multi-view and multi-scale visual features in the DETR3D-style. The refined proposals are end-to-end decoded into the detection results. To further boost the performance, we incorporate the auxiliary branches alongside the proposal generation to enhance the feature learning. Also, we design the methods of target filtering and teacher forcing to promote the consistency of two-stage training. We conduct extensive experiments on the 3D object detection benchmark of nuScenes to demonstrate the effectiveness of SimMOD and achieve new state-of-the-art performance. Code will be available at this https URL.

34.GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization ⬇️

Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain gap by using a causal framework for data generation. We assume that the real and synthetic data have common content variables but different style variables. Thus, a model trained on synthetic dataset might have poor generalization as the model learns the nuisance style variables. To that end, we propose causal invariance learning which encourages the model to learn a style-invariant representation that enhances the syn-to-real generalization. Furthermore, we propose a simple yet effective feature distillation method that prevents catastrophic forgetting of semantic knowledge of the real domain. In sum, we refer to our method as Guided Causal Invariant Syn-to-real Generalization that effectively improves the performance of syn-to-real generalization. We empirically verify the validity of proposed methods, and especially, our method achieves state-of-the-art on visual syn-to-real domain generalization tasks such as image classification and semantic segmentation.

35.FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning ⬇️

Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions, where lesions on darker skin types are usually underrepresented and have lower diagnosis accuracy, receives little attention. In this paper, we propose FairDisCo, a disentanglement deep learning framework with contrastive learning that utilizes an additional network branch to remove sensitive attributes, i.e. skin-type information from representations for fairness and another contrastive branch to enhance feature extraction. We compare FairDisCo to three fairness methods, namely, resampling, reweighting, and attribute-aware, on two newly released skin lesion datasets with different skin types: Fitzpatrick17k and Diverse Dermatology Images (DDI). We adapt two fairness-based metrics DPM and EOM for our multiple classes and sensitive attributes task, highlighting the skin-type bias in skin lesion classification. Extensive experimental evaluation demonstrates the effectiveness of FairDisCo, with fairer and superior performance on skin lesion classification tasks.

36.A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extraction ⬇️

In this paper, we introduce a new building dataset and propose a novel domain generalization method to facilitate the development of building extraction from high-resolution remote sensing images. The problem with the current building datasets involves that they lack diversity, the quality of the labels is unsatisfactory, and they are hardly used to train a building extraction model with good generalization ability, so as to properly evaluate the real performance of a model in practical scenes. To address these issues, we built a diverse, large-scale, and high-quality building dataset named the WHU-Mix building dataset, which is more practice-oriented. The WHU-Mix building dataset consists of a training/validation set containing 43,727 diverse images collected from all over the world, and a test set containing 8402 images from five other cities on five continents. In addition, to further improve the generalization ability of a building extraction model, we propose a domain generalization method named batch style mixing (BSM), which can be embedded as an efficient plug-and-play module in the frond-end of a building extraction model, providing the model with a progressively larger data distribution to learn data-invariant knowledge. The experiments conducted in this study confirmed the potential of the WHU-Mix building dataset to improve the performance of a building extraction model, resulting in a 6-36% improvement in mIoU, compared to the other existing datasets. The adverse impact of the inaccurate labels in the other datasets can cause about 20% IoU decrease. The experiments also confirmed the high performance of the proposed BSM module in enhancing the generalization ability and robustness of a model, exceeding the baseline model without domain generalization by 13% and the recent domain generalization methods by 4-15% in mIoU.

37.TransNet: Category-Level Transparent Object Pose Estimation ⬇️

Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain transparent surfaces with little specular reflection or refraction, e.g. glass doors, difficult to perceive. A second challenge is that common depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent objects due to their unique reflective properties. Stemming from these challenges, we observe that transparent object instances within the same category (e.g. cups) look more similar to each other than to ordinary opaque objects of that same category. Given this observation, the present paper sets out to explore the possibility of category-level transparent object pose estimation rather than instance-level pose estimation. We propose TransNet, a two-stage pipeline that learns to estimate category-level transparent object pose using localized depth completion and surface normal estimation. TransNet is evaluated in terms of pose estimation accuracy on a recent, large-scale transparent object dataset and compared to a state-of-the-art category-level pose estimation approach. Results from this comparison demonstrate that TransNet achieves improved pose estimation accuracy on transparent objects and key findings from the included ablation studies suggest future directions for performance improvements.

38.PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification ⬇️

Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, given the fact that it could be expensive in practice to annotate all labels in every training image. Existing works on partial-label learning focus on the case where each training image is annotated with only a subset of its labels. A special case is to annotate only one positive label in each training image. To further relieve the annotation burden and enhance the performance of the classifier, this paper proposes a new partial-label setting in which only a subset of the training images are labeled, each with only one positive label, while the rest of the training images remain unlabeled. To handle this new setting, we propose an end-to-end deep network, PLMCL (Partial Label Momentum Curriculum Learning), that can learn to produce confident pseudo labels for both partially-labeled and unlabeled training images. The novel momentum-based law updates soft pseudo labels on each training image with the consideration of the updating velocity of pseudo labels, which help avoid trapping to low-confidence local minimum, especially at the early stage of training in lack of both observed labels and confidence on pseudo labels. In addition, we present a confidence-aware scheduler to adaptively perform easy-to-hard learning for different labels. Extensive experiments demonstrate that our proposed PLMCL outperforms many state-of-the-art multi-label classification methods under various partial-label settings on three different datasets.

39.Equalization and Brightness Mapping Modes of Color-to-Gray Projection Operators ⬇️

In this article, the conversion of color RGB images to grayscale is covered by characterizing the mathematical operators used to project 3 color channels to a single one. Based on the fact that most operators assign each of the $256^3$ colors a single gray level, ranging from 0 to 255, they are clustering algorithms that distribute the color population into 256 clusters of increasing brightness. To visualize the way operators work the sizes of the clusters and the average brightness of each cluster are plotted. The equalization mode (EQ) introduced in this work focuses on cluster sizes, while the brightness mapping (BM) mode describes the CIE L* luminance distribution per cluster. Three classes of EQ modes and two classes of BM modes were found in linear operators, defining a 6-class taxonomy. The theoretical/methodological framework introduced was applied in a case study considering the equal-weights uniform operator, the NTSC standard operator, and an operator chosen as ideal to lighten the faces of black people to improve facial recognition in current biased classifiers. It was found that most current metrics used to assess the quality of color-to-gray conversions better assess one of the two BM mode classes, but the ideal operator chosen by a human team belongs to the other class. Therefore, this cautions against using these general metrics for specific purpose color-to-gray conversions. It should be noted that eventual applications of this framework to non-linear operators can give rise to new classes of EQ and BM modes. The main contribution of this article is to provide a tool to better understand color to gray converters in general, even those based on machine learning, within the current trend of better explainability of models.

40.Improving GANs for Long-Tailed Data through Group Spectral Regularization ⬇️

Deep long-tailed learning aims to train useful deep networks on practical, real-world imbalanced distributions, wherein most labels of the tail classes are associated with a few samples. There has been a large body of work to train discriminative models for visual recognition on long-tailed distribution. In contrast, we aim to train conditional Generative Adversarial Networks, a class of image generation models on long-tailed distributions. We find that similar to recognition, state-of-the-art methods for image generation also suffer from performance degradation on tail classes. The performance degradation is mainly due to class-specific mode collapse for tail classes, which we observe to be correlated with the spectral explosion of the conditioning parameter matrix. We propose a novel group Spectral Regularizer (gSR) that prevents the spectral explosion alleviating mode collapse, which results in diverse and plausible image generation even for tail classes. We find that gSR effectively combines with existing augmentation and regularization techniques, leading to state-of-the-art image generation performance on long-tailed data. Extensive experiments demonstrate the efficacy of our regularizer on long-tailed datasets with different degrees of imbalance.

41.A semi-supervised Teacher-Student framework for surgical tool detection and localization ⬇️

Surgical tool detection in minimally invasive surgery is an essential part of computer-assisted interventions. Current approaches are mostly based on supervised methods which require large fully labeled data to train supervised models and suffer from pseudo label bias because of class imbalance issues. However large image datasets with bounding box annotations are often scarcely available. Semi-supervised learning (SSL) has recently emerged as a means for training large models using only a modest amount of annotated data; apart from reducing the annotation cost. SSL has also shown promise to produce models that are more robust and generalizable. Therefore, in this paper we introduce a semi-supervised learning (SSL) framework in surgical tool detection paradigm which aims to mitigate the scarcity of training data and the data imbalance through a knowledge distillation approach. In the proposed work, we train a model with labeled data which initialises the Teacher-Student joint learning, where the Student is trained on Teacher-generated pseudo labels from unlabeled data. We propose a multi-class distance with a margin based classification loss function in the region-of-interest head of the detector to effectively segregate foreground classes from background region. Our results on m2cai16-tool-locations dataset indicate the superiority of our approach on different supervised data settings (1%, 2%, 5%, 10% of annotated data) where our model achieves overall improvements of 8%, 12% and 27% in mAP (on 1% labeled data) over the state-of-the-art SSL methods and a fully supervised baseline, respectively. The code is available at this https URL

42.Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation ⬇️

In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image serves as supervision for its strongly perturbed version. Intriguingly, we observe that such a simple pipeline already achieves competitive results against recent advanced works, when transferred to our segmentation scenario. Its success heavily relies on the manual design of strong data augmentations, however, which may be limited and inadequate to explore a broader perturbation space. Motivated by this, we propose an auxiliary feature perturbation stream as a supplement, leading to an expanded perturbation space. On the other, to sufficiently probe original image-level augmentations, we present a dual-stream perturbation technique, enabling two strong views to be simultaneously guided by a common weak view. Consequently, our overall Unified Dual-Stream Perturbations approach (UniMatch) surpasses all existing methods significantly across all evaluation protocols on the Pascal, Cityscapes, and COCO benchmarks. We also demonstrate the superiority of our method in remote sensing interpretation and medical image analysis. Code is available at this https URL.

43.SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms ⬇️

Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise recently. Rotation-equivariance and scale-equivariance are both critical in correspondence matching applications. Classical correspondence matching approaches are designed to withstand scaling and rotation transformations. However, the features extracted using convolutional neural networks (CNNs) are only translation-equivariant to a certain extent. Recently, researchers have strived to improve the rotation-equivariance of CNNs based on group theories. Sim(2) is the group of similarity transformations in the 2D plane. This paper presents a specialized dataset dedicated to evaluating sim(2)-equivariant correspondence matching algorithms. We compare the performance of 16 state-of-the-art (SoTA) correspondence matching approaches. The experimental results demonstrate the importance of group equivariant algorithms for correspondence matching on various sim(2) transformation conditions. Since the subpixel accuracy achieved by CNN-based correspondence matching approaches is unsatisfactory, this specific area requires more attention in future works. Our dataset is publicly available at: mias.group/SIM2E.

44.HST: Hierarchical Swin Transformer for Compressed Image Super-resolution ⬇️

Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to restore the distorted image with the simple cooperation of super-resolution and compression artifacts removing. In this paper, we take a step forward to propose the Hierarchical Swin Transformer (HST) network to restore the low-resolution compressed image, which jointly captures the hierarchical feature representations and enhances each-scale representation with Swin transformer, respectively. Moreover, we find that the pretraining with Super-resolution (SR) task is vital in compressed image super-resolution. To explore the effects of different SR pretraining, we take the commonly-used SR tasks (e.g., bicubic and different real super-resolution simulations) as our pretraining tasks, and reveal that SR plays an irreplaceable role in the compressed image super-resolution. With the cooperation of HST and pre-training, our HST achieves the fifth place in AIM 2022 challenge on the low-quality compressed image super-resolution track, with the PSNR of 23.51dB. Extensive experiments and ablation studies have validated the effectiveness of our proposed methods.

45.Masked Video Modeling with Correlation-aware Contrastive Learning for Breast Cancer Diagnosis in Ultrasound ⬇️

Breast cancer is one of the leading causes of cancer deaths in women. As the primary output of breast screening, breast ultrasound (US) video contains exclusive dynamic information for cancer diagnosis. However, training models for video analysis is non-trivial as it requires a voluminous dataset which is also expensive to annotate. Furthermore, the diagnosis of breast lesion faces unique challenges such as inter-class similarity and intra-class variation. In this paper, we propose a pioneering approach that directly utilizes US videos in computer-aided breast cancer diagnosis. It leverages masked video modeling as pretraning to reduce reliance on dataset size and detailed annotations. Moreover, a correlation-aware contrastive loss is developed to facilitate the identifying of the internal and external relationship between benign and malignant lesions. Experimental results show that our proposed approach achieved promising classification performance and can outperform other state-of-the-art methods.

46.DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection ⬇️

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text instances of arbitrary shapes and extreme aspect ratios. However, the bottom-up methods are limited to the performance of their segmentation models. In this paper, we propose DPTNet (Dual-Path Transformer Network), a simple yet effective architecture to model the global and local information for the scene text detection task. We further propose a parallel design that integrates the convolutional network with a powerful self-attention mechanism to provide complementary clues between the attention path and convolutional path. Moreover, a bi-directional interaction module across the two paths is developed to provide complementary clues in the channel and spatial dimensions. We also upgrade the concentration operation by adding an extra multi-head attention layer to it. Our DPTNet achieves state-of-the-art results on the MSRA-TD500 dataset, and provides competitive results on other standard benchmarks in terms of both detection accuracy and speed.

47.Objects Can Move: 3D Change Detection by Geometric Transformation Constistency ⬇️

AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not need to encode any assumptions about what is an object, but rather discovers objects by exploiting their coherent move. Changes are initially detected as differences in the depth maps and segmented as objects if they undergo rigid motions. A graph cut optimization propagates the changing labels to geometrically consistent regions. Experiments show that our method achieves state-of-the-art performance on the 3RScan dataset against competitive baselines. The source code of our method can be found at this https URL.

48.Semantic-enhanced Image Clustering ⬇️

Image clustering is an important, and open challenge task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus are unable to distinguish visually similar but semantically different images. In this paper, we propose to investigate the task of image clustering with the help of visual-language pre-training model. Different from the zero-shot setting in which the class names are known, we only know the number of clusters in this setting. Therefore, how to map images to a proper semantic space and how to cluster images from both image and semantic spaces are two key problems. To solve the above problems, we propose a novel image clustering method guided by the visual-language pre-training model CLIP, named as \textbf{Semantic-enhanced Image Clustering (SIC)}. In this new method, we propose a method to map the given images to a proper semantic space first and efficient methods to generate pseudo-labels according to the relationships between images and semantics. Finally, we propose to perform clustering with the consistency learning in both image space and semantic space, in a self-supervised learning fashion. Theoretical result on convergence analysis shows that our proposed method can converge in sublinear speed. Theoretical analysis on expectation risk also shows that we can reduce the expectation risk by improving the neighborhood consistency or prediction confidence or reducing neighborhood imbalance. Experimental results on five benchmark datasets clearly show the superiority of our new method.

49.Multi-task Learning for Monocular Depth and Defocus Estimations with Real Images ⬇️

Monocular depth estimation and defocus estimation are two fundamental tasks in computer vision. Most existing methods treat depth estimation and defocus estimation as two separate tasks, ignoring the strong connection between them. In this work, we propose a multi-task learning network consisting of an encoder with two decoders to estimate the depth and defocus map from a single focused image. Through the multi-task network, the depth estimation facilitates the defocus estimation to get better results in the weak texture region and the defocus estimation facilitates the depth estimation by the strong physical connection between the two maps. We set up a dataset (named ALL-in-3D dataset) which is the first all-real image dataset consisting of 100K sets of all-in-focus images, focused images with focus depth, depth maps, and defocus maps. It enables the network to learn features and solid physical connections between the depth and real defocus images. Experiments demonstrate that the network learns more solid features from the real focused images than the synthetic focused images. Benefiting from this multi-task structure where different tasks facilitate each other, our depth and defocus estimations achieve significantly better performance than other state-of-art algorithms. The code and dataset will be publicly available at this https URL.

50.CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification ⬇️

Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities. Its main challenge lies in the modality gap caused by cameras operating on different spectra. Existing VI-ReID methods mainly focus on learning general features across modalities, often at the expense of feature discriminability. To address this issue, we present a novel cycle-construction-based network for neutral yet discriminative feature learning, termed CycleTrans. Specifically, CycleTrans uses a lightweight Knowledge Capturing Module (KCM) to capture rich semantics from the modality-relevant feature maps according to pseudo queries. Afterwards, a Discrepancy Modeling Module (DMM) is deployed to transform these features into neutral ones according to the modality-irrelevant prototypes. To ensure feature discriminability, another two KCMs are further deployed for feature cycle constructions. With cycle construction, our method can learn effective neutral features for visible and infrared images while preserving their salient semantics. Extensive experiments on SYSU-MM01 and RegDB datasets validate the merits of CycleTrans against a flurry of state-of-the-art methods, +4.57% on rank-1 in SYSU-MM01 and +2.2% on rank-1 in RegDB.

51.CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval ⬇️

Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning is restricted by manually weighting negative pairs as well as unawareness of external knowledge. In this paper, we propose our novel Coupled Diversity-Sensitive Momentum Constrastive Learning (CODER) for improving cross-modal representation. Firstly, a novel diversity-sensitive contrastive learning (DCL) architecture is invented. We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting. Furthermore, two branches are designed in CODER. One learns instance-level embeddings from image/text, and it also generates pseudo online clustering labels for its input image/text based on their embeddings. Meanwhile, the other branch learns to query from commonsense knowledge graph to form concept-level descriptors for both modalities. Afterwards, both branches leverage DCL to align the cross-modal embedding spaces while an extra pseudo clustering label prediction loss is utilized to promote concept-level representation learning for the second branch. Extensive experiments conducted on two popular benchmarks, i.e. MSCOCO and Flicker30K, validate CODER remarkably outperforms the state-of-the-art approaches.

52.qDWI-Morph: Motion-compensated quantitative Diffusion-Weighted MRI analysis for fetal lung maturity assessment ⬇️

Quantitative analysis of fetal lung Diffusion-Weighted MRI (DWI) data shows potential in providing quantitative imaging biomarkers that indirectly reflect fetal lung maturation. However, fetal motion during the acquisition hampered quantitative analysis of the acquired DWI data and, consequently, reliable clinical utilization. We introduce qDWI-morph, an unsupervised deep-neural-network architecture for motion compensated quantitative DWI (qDWI) analysis. Our approach couples a registration sub-network with a quantitative DWI model fitting sub-network. We simultaneously estimate the qDWI parameters and the motion model by minimizing a bio-physically-informed loss function integrating a registration loss and a model fitting quality loss. We demonstrated the added-value of qDWI-morph over: 1) a baseline qDWI analysis without motion compensation and 2) a baseline deep-learning model incorporating registration loss solely. The qDWI-morph achieved a substantially improved correlation with the gestational age through in-vivo qDWI analysis of fetal lung DWI data (R-squared=0.32 vs. 0.13, 0.28). Our qDWI-morph has the potential to enable motion-compensated quantitative analysis of DWI data and to provide clinically feasible bio-markers for non-invasive fetal lung maturity assessment. Our code is available at: this https URL.

53.CenDerNet: Center and Curvature Representations for Render-and-Compare 6D Pose Estimation ⬇️

We introduce CenDerNet, a framework for 6D pose estimation from multi-view images based on center and curvature representations. Finding precise poses for reflective, textureless objects is a key challenge for industrial robotics. Our approach consists of three stages: First, a fully convolutional neural network predicts center and curvature heatmaps for each view; Second, center heatmaps are used to detect object instances and find their 3D centers; Third, 6D object poses are estimated using 3D centers and curvature heatmaps. By jointly optimizing poses across views using a render-and-compare approach, our method naturally handles occlusions and object symmetries. We show that CenDerNet outperforms previous methods on two industry-relevant datasets: DIMO and T-LESS.

54.Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation ⬇️

Unsupervised domain adaptation (UDA) is an approach to minimizing domain gap. Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e.g., cross-domain semantic segmentation. For aerial images, the digital surface model (DSM) is usually available in both the source domain and the target domain. Depth information in DSM brings external information to generative models. However, little research utilizes it. In this paper, depth-assisted ResiDualGAN (DRDG) is proposed where depth supervised loss (DSL), and depth cycle consistency loss (DCCL) are used to bring depth information into the generative model. Experimental results show that DRDG reaches state-of-the-art accuracy between generative methods in cross-domain semantic segmentation tasks.

55.LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction ⬇️

Hand reconstruction has achieved great success in real-time applications such as visual reality and augmented reality while interacting with two-hand reconstruction through efficient transformers is left unexplored. In this paper, we propose a method called lightweight attention hand (LWA-HAND) to reconstruct hands in low flops from a single RGB image. To solve the occlusion and interaction challenges in efficient attention architectures, we introduce three mobile attention modules. The first module is a lightweight feature attention module that extracts both local occlusion representation and global image patch representation in a coarse-to-fine manner. The second module is a cross image and graph bridge module which fuses image context and hand vertex. The third module is a lightweight cross-attention mechanism that uses element-wise operation for cross attention of two hands in linear complexity. The resulting model achieves comparable performance on the InterHand2.6M benchmark in comparison with the state-of-the-art models. Simultaneously, it reduces the flops to $0.47GFlops$ while the state-of-the-art models have heavy computations between $10GFlops$ and $20GFlops$.

56.PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition ⬇️

3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in the physical world, deep learning is notorious for its vulnerability to adversarial attacks. In this work, we first identify that the state-of-the-art empirical defense, adversarial training, has a major limitation in applying to 3D point cloud models due to gradient obfuscation. We further propose PointDP, a purification strategy that leverages diffusion models to defend against 3D adversarial attacks. We extensively evaluate PointDP on six representative 3D point cloud architectures, and leverage 10+ strong and adaptive attacks to demonstrate its lower-bound robustness. Our evaluation shows that PointDP achieves significantly better robustness than state-of-the-art purification methods under strong attacks. Results of certified defenses on randomized smoothing combined with PointDP will be included in the near future.

57.Towards MOOCs for Lip Reading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale ⬇️

Many people with some form of hearing loss consider lipreading as their primary mode of day-to-day communication. However, finding resources to learn or improve one's lipreading skills can be challenging. This is further exacerbated in COVID$19$ pandemic due to restrictions on direct interactions with peers and speech therapists. Today, online MOOCs platforms like Coursera and Udemy have become the most effective form of training for many kinds of skill development. However, online lipreading resources are scarce as creating such resources is an extensive process needing months of manual effort to record hired actors. Because of the manual pipeline, such platforms are also limited in the vocabulary, supported languages, accents, and speakers, and have a high usage cost. In this work, we investigate the possibility of replacing real human talking videos with synthetically generated videos. Synthetic data can be used to easily incorporate larger vocabularies, variations in accent, and even local languages, and many speakers. We propose an end-to-end automated pipeline to develop such a platform using state-of-the-art talking heading video generator networks, text-to-speech models, and computer vision techniques. We then perform an extensive human evaluation using carefully thought out lipreading exercises to validate the quality of our designed platform against the existing lipreading platforms. Our studies concretely point towards the potential of our approach for the development of a large-scale lipreading MOOCs platform that can impact millions of people with hearing loss.

58.FaceOff: A Video-to-Video Face Swapping System ⬇️

Doubles play an indispensable role in the movie industry. They take the place of the actors in dangerous stunt scenes or in scenes where the same actor plays multiple characters. The double's face is later replaced with the actor's face and expressions manually using expensive CGI technology, costing millions of dollars and taking months to complete. An automated, inexpensive, and fast way can be to use face-swapping techniques that aim to swap an identity from a source face video (or an image) to a target face video. However, such methods can not preserve the source expressions of the actor important for the scene's context. % essential for the scene. % that are essential in cinemas. To tackle this challenge, we introduce video-to-video (V2V) face-swapping, a novel task of face-swapping that can preserve (1) the identity and expressions of the source (actor) face video and (2) the background and pose of the target (double) video. We propose FaceOff, a V2V face-swapping system that operates by learning a robust blending operation to merge two face videos following the constraints above. It first reduces the videos to a quantized latent space and then blends them in the reduced space. FaceOff is trained in a self-supervised manner and robustly tackles the non-trivial challenges of V2V face-swapping. As shown in the experimental section, FaceOff significantly outperforms alternate approaches qualitatively and quantitatively.

59.RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking ⬇️

RGB-D object tracking has attracted considerable attention recently, achieving promising performance thanks to the symbiosis between visual and depth channels. However, given a limited amount of annotated RGB-D tracking data, most state-of-the-art RGB-D trackers are simple extensions of high-performance RGB-only trackers, without fully exploiting the underlying potential of the depth channel in the offline training stage. To address the dataset deficiency issue, a new RGB-D dataset named RGBD1K is released in this paper. The RGBD1K contains 1,050 sequences with about 2.5M frames in total. To demonstrate the benefits of training on a larger RGB-D data set in general, and RGBD1K in particular, we develop a transformer-based RGB-D tracker, named SPT, as a baseline for future visual object tracking studies using the new dataset. The results, of extensive experiments using the SPT tracker emonstrate the potential of the RGBD1K dataset to improve the performance of RGB-D tracking, inspiring future developments of effective tracker designs. The dataset and codes will be available on the project homepage: https://will.be.available.at.this.website.

60.JVLDLoc: a Joint Optimization of Visual-LiDAR Constraints and Direction Priors for Localization in Driving Scenario ⬇️

The ability for a moving agent to localize itself in environment is the basic demand for emerging applications, such as autonomous driving, etc. Many existing methods based on multiple sensors still suffer from drift. We propose a scheme that fuses map prior and vanishing points from images, which can establish an energy term that is only constrained on rotation, called the direction projection error. Then we embed these direction priors into a visual-LiDAR SLAM system that integrates camera and LiDAR measurements in a tightly-coupled way at backend. Specifically, our method generates visual reprojection error and point to Implicit Moving Least Square(IMLS) surface of scan constraints, and solves them jointly along with direction projection error at global optimization. Experiments on KITTI, KITTI-360 and Oxford Radar Robotcar show that we achieve lower localization error or Absolute Pose Error (APE) than prior map, which validates our method is effective.

61.Artifact-Based Domain Generalization of Skin Lesion Models ⬇️

Deep Learning failure cases are abundant, particularly in the medical area. Recent studies in out-of-distribution generalization have advanced considerably on well-controlled synthetic datasets, but they do not represent medical imaging contexts. We propose a pipeline that relies on artifacts annotation to enable generalization evaluation and debiasing for the challenging skin lesion analysis context. First, we partition the data into levels of increasingly higher biased training and test sets for better generalization assessment. Then, we create environments based on skin lesion artifacts to enable domain generalization methods. Finally, after robust training, we perform a test-time debiasing procedure, reducing spurious features in inference images. Our experiments show our pipeline improves performance metrics in biased cases, and avoids artifacts when using explanation methods. Still, when evaluating such models in out-of-distribution data, they did not prefer clinically-meaningful features. Instead, performance only improved in test sets that present similar artifacts from training, suggesting models learned to ignore the known set of artifacts. Our results raise a concern that debiasing models towards a single aspect may not be enough for fair skin lesion analysis.

62.Learning Primitive-aware Discriminative Representations for FSL ⬇️

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to recognize novel classes,given only a few labeled examples per class.Limited data keep this task challenging for deep learning.Recent metric-based methods has achieved promising performance based on image-level features.However,these global features ignore abundant local and structural information that is transferable and consistent between seen and unseen classes.Some study in cognitive science argue that humans can recognize novel classes with the learned primitives.We expect to mine both transferable and discriminative representation from base classes and adopt them to recognize novel classes.Building on the episodic training mechanism,We propose a Primitive Mining and Reasoning Network(PMRN) to learn primitive-aware representation in an end-to-end manner for metric-based FSL model.We first add self-supervision auxiliary task,forcing feature extractor to learn tvisual pattern corresponding to this http URL further mine and produce transferable primitive-aware representations,we design an Adaptive Channel Grouping(ACG)module to synthesize a set of visual primitives from object embedding by enhancing informative channel maps while suppressing useless ones. Based on the learned primitive feature,a Semantic Correlation Reasoning (SCR) module is proposed to capture internal relations among them.Finally,we learn the task-specific importance of primitives and conduct primitive-level metric based on the task-specific attention feature.Extensive experiments show that our method achieves state-of-the-art results on six standard benchmarks.

63.DenseShift: Towards Accurate and Transferable Low-Bit Shift Network ⬇️

Deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. Recent investigations propose multiplication-free neural networks to reduce computation and memory consumption. Shift neural network is one of the most effective tools towards these reductions. However, existing low-bit shift networks are not as accurate as their full precision counterparts and cannot efficiently transfer to a wide range of tasks due to their inherent design flaws. We propose DenseShift network that exploits the following novel designs. First, we demonstrate that the zero-weight values in low-bit shift networks are neither useful to the model capacity nor simplify the model inference. Therefore, we propose to use a zero-free shifting mechanism to simplify inference while increasing the model capacity. Second, we design a new metric to measure the weight freezing issue in training low-bit shift networks, and propose a sign-scale decomposition to improve the training efficiency. Third, we propose the low-variance random initialization strategy to improve the model's performance in transfer learning scenarios. We run extensive experiments on various computer vision and speech tasks. The experimental results show that DenseShift network significantly outperforms existing low-bit multiplication-free networks and can achieve competitive performance to the full-precision counterpart. It also exhibits strong transfer learning performance with no drop in accuracy.

64.SnowFormer: Scale-aware Transformer via Context Interaction for Single Image Desnowing ⬇️

Single image desnowing is a common yet challenging task. The complex snow degradations and diverse degradation scales demand strong representation ability. In order for the desnowing network to see various snow degradations and model the context interaction of local details and global information, we propose a powerful architecture dubbed as SnowFormer. First, it performs Scale-aware Feature Aggregation in the encoder to capture rich snow information of various degradations. Second, in order to tackle with large-scale degradation, it uses a novel Context Interaction Transformer Block in the decoder, which conducts context interaction of local details and global information from previous scale-aware feature aggregation in global context interaction. And the introduction of local context interaction improves recovery of scene details. Third, we devise a Heterogeneous Feature Projection Head which progressively fuse features from both the encoder and decoder and project the refined feature into the clean image. Extensive experiments demonstrate that the proposed SnowFormer achieves significant improvements over other SOTA methods. Compared with SOTA single image desnowing method HDCW-Net, it boosts the PSNR metric by 9.2dB on the CSD testset. Moreover, it also achieves a 5.13dB increase in PSNR compared with general image restoration architecture NAFNet, which verifies the strong representation ability of our SnowFormer for snow removal task. The code is released in \url{this https URL}.

65.Fuse and Attend: Generalized Embedding Learning for Art and Sketches ⬇️

While deep Embedding Learning approaches have witnessed widespread success in multiple computer vision tasks, the state-of-the-art methods for representing natural images need not necessarily perform well on images from other domains, such as paintings, cartoons, and sketch. This is because of the huge shift in the distribution of data from across these domains, as compared to natural images. Domains like sketch often contain sparse informative pixels. However, recognizing objects in such domains is crucial, given multiple relevant applications leveraging such data, for instance, sketch to image retrieval. Thus, achieving an Embedding Learning model that could perform well across multiple domains is not only challenging, but plays a pivotal role in computer vision. To this end, in this paper, we propose a novel Embedding Learning approach with the goal of generalizing across different domains. During training, given a query image from a domain, we employ gated fusion and attention to generate a positive example, which carries a broad notion of the semantics of the query object category (from across multiple domains). By virtue of Contrastive Learning, we pull the embeddings of the query and positive, in order to learn a representation which is robust across domains. At the same time, to teach the model to be discriminative against examples from different semantic categories (across domains), we also maintain a pool of negative embeddings (from different categories). We show the prowess of our method using the DomainBed framework, on the popular PACS (Photo, Art painting, Cartoon, and Sketch) dataset.

66.Effectiveness of Function Matching in Driving Scene Recognition ⬇️

Knowledge distillation is an effective approach for training compact recognizers required in autonomous driving. Recent studies on image classification have shown that matching student and teacher on a wide range of data points is critical for improving performance in distillation. This concept (called function matching) is suitable for driving scene recognition, where generally an almost infinite amount of unlabeled data are available. In this study, we experimentally investigate the impact of using such a large amount of unlabeled data for distillation on the performance of student models in structured prediction tasks for autonomous driving. Through extensive experiments, we demonstrate that the performance of the compact student model can be improved dramatically and even match the performance of the large-scale teacher by knowledge distillation with massive unlabeled data.

67.Learning Sub-Pixel Disparity Distribution for Light Field Depth Estimation ⬇️

Existing light field (LF) depth estimation methods generally consider depth estimation as a regression problem, supervised by a pixel-wise L1 loss between the regressed disparity map and the groundtruth one. However, the disparity map is only a sub-space projection (i.e., an expectation) of the disparity distribution, while the latter one is more essential for models to learn. In this paper, we propose a simple yet effective method to learn the sub-pixel disparity distribution by fully utilizing the power of deep networks. In our method, we construct the cost volume at sub-pixel level to produce a finer depth distribution and design an uncertainty-aware focal loss to supervise the disparity distribution to be close to the groundtruth one. Extensive experimental results demonstrate the effectiveness of our method. Our method, called SubFocal, ranks the first place among 99 submitted algorithms on the HCI 4D LF Benchmark in terms of all the five accuracy metrics (i.e., BadPix0.01, BadPix0.03, BadPix0.07, MSE and Q25), and significantly outperforms recent state-of-the-art LF depth methods such as OACC-Net and AttMLFNet. Code and model are available at this https URL.

68.YOLOV: Making Still Image Object Detectors Great at Video Object Detection ⬇️

Video object detection (VID) is challenging because of the high variation of object appearance as well as the diverse deterioration in some frames. On the positive side, the detection in a certain frame of a video, compared with in a still image, can draw support from other frames. Hence, how to aggregate features across different frames is pivotal to the VID problem. Most of existing aggregation algorithms are customized for two-stage detectors. But, the detectors in this category are usually computationally expensive due to the two-stage nature. This work proposes a simple yet effective strategy to address the above concerns, which spends marginal overheads with significant gains in accuracy. Concretely, different from the traditional two-stage pipeline, we advocate putting the region-level selection after the one-stage detection to avoid processing massive low-quality candidates. Besides, a novel module is constructed to evaluate the relationship between a target frame and its reference ones, and guide the aggregation. Extensive experiments and ablation studies are conducted to verify the efficacy of our design, and reveal its superiority over other state-of-the-art VID approaches in both effectiveness and efficiency. Our YOLOX-based model can achieve promising performance (e.g., 87.5% AP50 at over 30 FPS on the ImageNet VID dataset on a single 2080Ti GPU), making it attractive for large-scale or real-time applications. The implementation is simple, the demo code and models have been made available at this https URL .

69.Finding Emotions in Faces: A Meta-Classifier ⬇️

Machine learning has been used to recognize emotions in faces, typically by looking for 8 different emotional states (neutral, happy, sad, surprise, fear, disgust, anger and contempt). We consider two approaches: feature recognition based on facial landmarks and deep learning on all pixels; each produced 58% overall accuracy. However, they produced different results on different images and thus we propose a new meta-classifier combining these approaches. It produces far better results with 77% accuracy

70.Net2Brain: A Toolbox to compare artificial vision models with human brain responses ⬇️

We introduce Net2Brain, a graphical and command-line user interface toolbox for comparing the representational spaces of artificial deep neural networks (DNNs) and human brain recordings. While different toolboxes facilitate only single functionalities or only focus on a small subset of supervised image classification models, Net2Brain allows the extraction of activations of more than 600 DNNs trained to perform a diverse range of vision-related tasks (e.g semantic segmentation, depth estimation, action recognition, etc.), over both image and video datasets. The toolbox computes the representational dissimilarity matrices (RDMs) over those activations and compares them to brain recordings using representational similarity analysis (RSA), weighted RSA, both in specific ROIs and with searchlight search. In addition, it is possible to add a new data set of stimuli and brain recordings to the toolbox for evaluation. We demonstrate the functionality and advantages of Net2Brain with an example showcasing how it can be used to test hypotheses of cognitive computational neuroscience.

71.Generalised Co-Salient Object Detection ⬇️

Conventional co-salient object detection (CoSOD) has a strong assumption that \enquote{a common salient object exists in every image of the same group}. However, the biased assumption contradicts real scenarios where co-salient objects could be partially or completely absent in a group of images. We propose a random sampling based Generalised CoSOD Training (GCT) strategy to distill the awareness of inter-image absence of co-salient object(s) into CoSOD models. In addition, the random sampling process inherent in GCT enables the generation of a high-quality uncertainty map, with which we can further remediate less confident model predictions that are prone to localising non-common salient objects. To evaluate the generalisation ability of CoSOD models, we propose two new testing datasets, namely CoCA-Common and CoCA-Zero, where a common salient object is partially present in the former and completely absent in the latter. Extensive experiments demonstrate that our proposed method significantly improves the generalisation ability of CoSOD models on the two new datasets, while not negatively impacting its performance under the conventional CoSOD setting. Codes are available at this https URL.

72.Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics ⬇️

Assessing image aesthetics is a challenging computer vision task. One reason is that aesthetic preference is highly subjective and may vary significantly among people for certain images. Thus, it is important to properly model and quantify such \textit{subjectivity}, but there has not been much effort to resolve this issue. In this paper, we propose a novel unified probabilistic framework that can model and quantify subjective aesthetic preference based on the subjective logic. In this framework, the rating distribution is modeled as a beta distribution, from which the probabilities of being definitely pleasing, being definitely unpleasing, and being uncertain can be obtained. We use the probability of being uncertain to define an intuitive metric of subjectivity. Furthermore, we present a method to learn deep neural networks for prediction of image aesthetics, which is shown to be effective in improving the performance of subjectivity prediction via experiments. We also present an application scenario where the framework is beneficial for aesthetics-based image recommendation.

73.Offline Handwritten Mathematical Recognition using Adversarial Learning and Transformers ⬇️

Offline Handwritten Mathematical Expression Recognition (HMER) is a major area in the field of mathematical expression recognition. Offline HMER is often viewed as a much harder problem as compared to online HMER due to a lack of temporal information and variability in writing style. In this paper, we purpose a encoder-decoder model that uses paired adversarial learning. Semantic-invariant features are extracted from handwritten mathematical expression images and their printed mathematical expression counterpart in the encoder. Learning of semantic-invariant features combined with the DenseNet encoder and transformer decoder, helped us to improve the expression rate from previous studies. Evaluated on the CROHME dataset, we have been able to improve latest CROHME 2019 test set results by 4% approx.

74.A Visual Analytics Framework for Composing a Hierarchical Classification for Medieval Illuminations ⬇️

Annotated data is a requirement for applying supervised machine learning methods, and the quality of annotations is crucial for the result. Especially when working with cultural heritage collections that inhere a manifold of uncertainties, annotating data remains a manual, arduous task to be carried out by domain experts. Our project started with two already annotated sets of medieval manuscript images which however were incomplete and comprised conflicting metadata based on scholarly and linguistic differences. Our aims were to create (1) a uniform set of descriptive labels for the combined data set, and (2) a hierarchical classification of a high quality that can be used as a valuable input for supervised machine learning. To reach these goals, we developed a visual analytics system to enable medievalists to combine, regularize and extend the vocabulary used to describe these data sets. Visual interfaces for word and image embeddings as well as co-occurrences of the annotations across the data sets enable annotating multiple images at the same time, recommend annotation label candidates and support composing a hierarchical classification of labels. Our system itself implements a semi-supervised method as it updates visual representations based on the medievalists' feedback, and a series of usage scenarios document its value for the target community.

75.MemoNav: Selecting Informative Memories for Visual Navigation ⬇️

Image-goal navigation is a challenging task, as it requires the agent to navigate to a target indicated by an image in a previously unseen scene. Current methods introduce diverse memory mechanisms which save navigation history to solve this task. However, these methods use all observations in the memory for generating navigation actions without considering which fraction of this memory is informative. To address this limitation, we present the MemoNav, a novel memory mechanism for image-goal navigation, which retains the agent's informative short-term memory and long-term memory to improve the navigation performance on a multi-goal task. The node features on the agent's topological map are stored in the short-term memory, as these features are dynamically updated. To aid the short-term memory, we also generate long-term memory by continuously aggregating the short-term memory via a graph attention module. The MemoNav retains the informative fraction of the short-term memory via a forgetting module based on a Transformer decoder and then incorporates this retained short-term memory and the long-term memory into working memory. Lastly, the agent uses the working memory for action generation. We evaluate our model on a new multi-goal navigation dataset. The experimental results show that the MemoNav outperforms the SoTA methods by a large margin with a smaller fraction of navigation history. The results also empirically show that our model is less likely to be trapped in a deadlock, which further validates that the MemoNav improves the agent's navigation efficiency by reducing redundant steps.

76.Analyzing Adversarial Robustness of Vision Transformers against Spatial and Spectral Attacks ⬇️

Vision Transformers have emerged as a powerful architecture that can outperform convolutional neural networks (CNNs) in image classification tasks. Several attempts have been made to understand robustness of Transformers against adversarial attacks, but existing studies draw inconsistent results, i.e., some conclude that Transformers are more robust than CNNs, while some others find that they have similar degrees of robustness. In this paper, we address two issues unexplored in the existing studies examining adversarial robustness of Transformers. First, we argue that the image quality should be simultaneously considered in evaluating adversarial robustness. We find that the superiority of one architecture to another in terms of robustness can change depending on the attack strength expressed by the quality of the attacked images. Second, by noting that Transformers and CNNs rely on different types of information in images, we formulate an attack framework, called Fourier attack, as a tool for implementing flexible attacks, where an image can be attacked in the spectral domain as well as in the spatial domain. This attack perturbs the magnitude and phase information of particular frequency components selectively. Through extensive experiments, we find that Transformers tend to rely more on phase information and low frequency information than CNNs, and thus sometimes they are even more vulnerable under frequency-selective attacks. It is our hope that this work provides new perspectives in understanding the properties and adversarial robustness of Transformers.

77.Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks ⬇️

Text-to-image synthesis aims to generate a photo-realistic and semantic consistent image from a specific text description. The images synthesized by off-the-shelf models usually contain limited components compared with the corresponding image and text description, which decreases the image quality and the textual-visual consistency. To address this issue, we propose a novel Vision-Language Matching strategy for text-to-image synthesis, named VLMGAN*, which introduces a dual vision-language matching mechanism to strengthen the image quality and semantic consistency. The dual vision-language matching mechanism considers textual-visual matching between the generated image and the corresponding text description, and visual-visual consistent constraints between the synthesized image and the real image. Given a specific text description, VLMGAN* firstly encodes it into textual features and then feeds them to a dual vision-language matching-based generative model to synthesize a photo-realistic and textual semantic consistent image. Besides, the popular evaluation metrics for text-to-image synthesis are borrowed from simple image generation, which mainly evaluates the reality and diversity of the synthesized images. Therefore, we introduce a metric named Vision-Language Matching Score (VLMS) to evaluate the performance of text-to-image synthesis which can consider both the image quality and the semantic consistency between synthesized image and the description. The proposed dual multi-level vision-language matching strategy can be applied to other text-to-image synthesis methods. We implement this strategy on two popular baselines, which are marked with ${\text{VLMGAN}{+\text{AttnGAN}}}$ and ${\text{VLMGAN}{+\text{DFGAN}}}$. The experimental results on two widely-used datasets show that the model achieves significant improvements over other state-of-the-art methods.

78.Transforming the Interactive Segmentation for Medical Imaging ⬇️

The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available annotations or the difficulty nature of the problem itself, for example, on segmenting cancer or small organs. Specifically, we propose a novel Transformer-based architecture for Interactive Segmentation (TIS), that treats the refinement task as a procedure for grouping pixels with similar features to those clicks given by the end users. Our proposed architecture is composed of Transformer Decoder variants, which naturally fulfills feature comparison with the attention mechanisms. In contrast to existing approaches, our proposed TIS is not limited to binary segmentations, and allows the user to edit masks for arbitrary number of categories. To validate the proposed approach, we conduct extensive experiments on three challenging datasets and demonstrate superior performance over the existing state-of-the-art methods. The project page is: this https URL.

79.Review on Action Recognition for Accident Detection in Smart City Transportation Systems ⬇️

Action detection and public traffic safety are crucial aspects of a safe community and a better society. Monitoring traffic flows in a smart city using different surveillance cameras can play a significant role in recognizing accidents and alerting first responders. The utilization of action recognition (AR) in computer vision tasks has contributed towards high-precision applications in video surveillance, medical imaging, and digital signal processing. This paper presents an intensive review focusing on action recognition in accident detection and autonomous transportation systems for a smart city. In this paper, we focused on AR systems that used diverse sources of traffic video capturing, such as static surveillance cameras on traffic intersections, highway monitoring cameras, drone cameras, and dash-cams. Through this review, we identified the primary techniques, taxonomies, and algorithms used in AR for autonomous transportation and accident detection. We also examined data sets utilized in the AR tasks, identifying the main sources of datasets and features of the datasets. This paper provides potential research direction to develop and integrate accident detection systems for autonomous cars and public traffic safety systems by alerting emergency personnel and law enforcement in the event of road accidents to minimize human error in accident reporting and provide a spontaneous response to victims

80.Learning in Audio-visual Context: A Review, Analysis, and New Perspective ⬇️

Sight and hearing are two senses that play a vital role in human communication and scene understanding. To mimic human perception ability, audio-visual learning, aimed at developing computational approaches to learn from both audio and visual modalities, has been a flourishing field in recent years. A comprehensive survey that can systematically organize and analyze studies of the audio-visual field is expected. Starting from the analysis of audio-visual cognition foundations, we introduce several key findings that have inspired our computational studies. Then, we systematically review the recent audio-visual learning studies and divide them into three categories: audio-visual boosting, cross-modal perception and audio-visual collaboration. Through our analysis, we discover that, the consistency of audio-visual data across semantic, spatial and temporal support the above studies. To revisit the current development of the audio-visual learning field from a more macro view, we further propose a new perspective on audio-visual scene understanding, then discuss and analyze the feasible future direction of the audio-visual learning area. Overall, this survey reviews and outlooks the current audio-visual learning field from different aspects. We hope it can provide researchers with a better understanding of this area. A website including constantly-updated survey is released: \url{this https URL}.

81.Contrastive Domain Adaptation for Early Misinformation Detection: A Case Study on COVID-19 ⬇️

Despite recent progress in improving the performance of misinformation detection systems, classifying misinformation in an unseen domain remains an elusive challenge. To address this issue, a common approach is to introduce a domain critic and encourage domain-invariant input features. However, early misinformation often demonstrates both conditional and label shifts against existing misinformation data (e.g., class imbalance in COVID-19 datasets), rendering such methods less effective for detecting early misinformation. In this paper, we propose contrastive adaptation network for early misinformation detection (CANMD). Specifically, we leverage pseudo labeling to generate high-confidence target examples for joint training with source data. We additionally design a label correction component to estimate and correct the label shifts (i.e., class priors) between the source and target domains. Moreover, a contrastive adaptation loss is integrated in the objective function to reduce the intra-class discrepancy and enlarge the inter-class discrepancy. As such, the adapted model learns corrected class priors and an invariant conditional distribution across both domains for improved estimation of the target data distribution. To demonstrate the effectiveness of the proposed CANMD, we study the case of COVID-19 early misinformation detection and perform extensive experiments using multiple real-world datasets. The results suggest that CANMD can effectively adapt misinformation detection systems to the unseen COVID-19 target domain with significant improvements compared to the state-of-the-art baselines.

82.Multiple Instance Neuroimage Transformer ⬇️

For the first time, we propose using a multiple instance learning based convolution-free transformer model, called Multiple Instance Neuroimage Transformer (MINiT), for the classification of T1weighted (T1w) MRIs. We first present several variants of transformer models adopted for neuroimages. These models extract non-overlapping 3D blocks from the input volume and perform multi-headed self-attention on a sequence of their linear projections. MINiT, on the other hand, treats each of the non-overlapping 3D blocks of the input MRI as its own instance, splitting it further into non-overlapping 3D patches, on which multi-headed self-attention is computed. As a proof-of-concept, we evaluate the efficacy of our model by training it to identify sex from T1w-MRIs of two public datasets: Adolescent Brain Cognitive Development (ABCD) and the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA). The learned attention maps highlight voxels contributing to identifying sex differences in brain morphometry. The code is available at this https URL.

83.A Dual Modality Approach For (Zero-Shot) Multi-Label Classification ⬇️

In computer vision, multi-label classification, including zero-shot multi-label classification are important tasks with many real-world applications. In this paper, we propose a novel algorithm, Aligned Dual moDality ClaSsifier (ADDS), which includes a Dual-Modal decoder (DM-decoder) with alignment between visual and textual features, for multi-label classification tasks. Moreover, we design a simple and yet effective method called Pyramid-Forwarding to enhance the performance for inputs with high resolutions. Extensive experiments conducted on standard multi-label benchmark datasets, MS-COCO and NUS-WIDE, demonstrate that our approach significantly outperforms previous methods and provides state-of-the-art performance for conventional multi-label classification, zero-shot multi-label classification, and an extreme case called single-to-multi label classification where models trained on single-label datasets (ImageNet-1k, ImageNet-21k) are tested on multi-label ones (MS-COCO and NUS-WIDE). We also analyze how visual-textual alignment contributes to the proposed approach, validate the significance of the DM-decoder, and demonstrate the effectiveness of Pyramid-Forwarding on vision transformer.

84.Accelerating Vision Transformer Training via a Patch Sampling Schedule ⬇️

We introduce the notion of a Patch Sampling Schedule (PSS), that varies the number of Vision Transformer (ViT) patches used per batch during training. Since all patches are not equally important for most vision objectives (e.g., classification), we argue that less important patches can be used in fewer training iterations, leading to shorter training time with minimal impact on performance. Additionally, we observe that training with a PSS makes a ViT more robust to a wider patch sampling range during inference. This allows for a fine-grained, dynamic trade-off between throughput and accuracy during inference. We evaluate using PSSs on ViTs for ImageNet both trained from scratch and pre-trained using a reconstruction loss function. For the pre-trained model, we achieve a 0.26% reduction in classification accuracy for a 31% reduction in training time (from 25 to 17 hours) compared to using all patches each iteration. Code, model checkpoints and logs are available at this https URL.

85.Explainable Biometrics in the Age of Deep Learning ⬇️

Systems capable of analyzing and quantifying human physical or behavioral traits, known as biometrics systems, are growing in use and application variability. Since its evolution from handcrafted features and traditional machine learning to deep learning and automatic feature extraction, the performance of biometric systems increased to outstanding values. Nonetheless, the cost of this fast progression is still not understood. Due to its opacity, deep neural networks are difficult to understand and analyze, hence, hidden capacities or decisions motivated by the wrong motives are a potential risk. Researchers have started to pivot their focus towards the understanding of deep neural networks and the explanation of their predictions. In this paper, we provide a review of the current state of explainable biometrics based on the study of 47 papers and discuss comprehensively the direction in which this field should be developed.

86.BARReL: Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning ⬇️

Robustness to adversarial perturbations has been explored in many areas of computer vision. This robustness is particularly relevant in vision-based reinforcement learning, as the actions of autonomous agents might be safety-critic or impactful in the real world. We investigate the susceptibility of vision-based reinforcement learning agents to gradient-based adversarial attacks and evaluate a potential defense. We observe that Bottleneck Attention Modules (BAM) included in CNN architectures can act as potential tools to increase robustness against adversarial attacks. We show how learned attention maps can be used to recover activations of a convolutional layer by restricting the spatial activations to salient regions. Across a number of RL environments, BAM-enhanced architectures show increased robustness during inference. Finally, we discuss potential future research directions.

87.Optimising Chest X-Rays for Image Analysis by Identifying and Removing Confounding Factors ⬇️

During the COVID-19 pandemic, the sheer volume of imaging performed in an emergency setting for COVID-19 diagnosis has resulted in a wide variability of clinical CXR acquisitions. This variation is seen in the CXR projections used, image annotations added and in the inspiratory effort and degree of rotation of clinical images. The image analysis community has attempted to ease the burden on overstretched radiology departments during the pandemic by developing automated COVID-19 diagnostic algorithms, the input for which has been CXR imaging. Large publicly available CXR datasets have been leveraged to improve deep learning algorithms for COVID-19 diagnosis. Yet the variable quality of clinically-acquired CXRs within publicly available datasets could have a profound effect on algorithm performance. COVID-19 diagnosis may be inferred by an algorithm from non-anatomical features on an image such as image labels. These imaging shortcuts may be dataset-specific and limit the generalisability of AI systems. Understanding and correcting key potential biases in CXR images is therefore an essential first step prior to CXR image analysis. In this study, we propose a simple and effective step-wise approach to pre-processing a COVID-19 chest X-ray dataset to remove undesired biases. We perform ablation studies to show the impact of each individual step. The results suggest that using our proposed pipeline could increase accuracy of the baseline COVID-19 detection algorithm by up to 13%.

88.Learning Low Bending and Low Distortion Manifold Embeddings: Theory and Applications ⬇️

Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the decoder represents the inverse map, providing a parametrization of the data manifold by the manifold in latent space. A good regularity and structure of the embedded manifold may substantially simplify further data processing tasks such as cluster analysis or data interpolation. We propose and analyze a novel regularization for learning the encoder component of an autoencoder: a loss functional that prefers isometric, extrinsically flat embeddings and allows to train the encoder on its own. To perform the training it is assumed that for pairs of nearby points on the input manifold their local Riemannian distance and their local Riemannian average can be evaluated. The loss functional is computed via Monte Carlo integration with different sampling strategies for pairs of points on the input manifold. Our main theorem identifies a geometric loss functional of the embedding map as the $\Gamma$-limit of the sampling-dependent loss functionals. Numerical tests, using image data that encodes different explicitly given data manifolds, show that smooth manifold embeddings into latent space are obtained. Due to the promotion of extrinsic flatness, these embeddings are regular enough such that interpolation between not too distant points on the manifold is well approximated by linear interpolation in latent space as one possible postprocessing.

89.Noise-Adaptive Intelligent Programmable Meta-Imager ⬇️

We present an intelligent programmable computational meta-imager that tailors its sequence of coherent scene illuminations not only to a specific information-extraction task (e.g., object recognition) but also adapts to different types and levels of noise. We systematically study how the learned illumination patterns depend on the noise, and we discover that trends in intensity and overlap of the learned illumination patterns can be understood intuitively. We conduct our analysis based on an analytical coupled-dipole forward model of a microwave dynamic metasurface antenna (DMA); we formulate a differentiable end-to-end information-flow pipeline comprising the programmable physical measurement process including noise as well as the subsequent digital processing layers. This pipeline allows us to jointly inverse-design the programmable physical weights (DMA configurations that determine the coherent scene illuminations) and the trainable digital weights. Our noise-adaptive intelligent meta-imager outperforms the conventional use of pseudo-random illumination patterns most clearly under conditions that make the extraction of sufficient task-relevant information challenging: latency constraints (limiting the number of allowed measurements) and strong noise. Programmable microwave meta-imagers in indoor surveillance and earth observation will be confronted with these conditions.

90.A Web Application for Experimenting and Validating Remote Measurement of Vital Signs ⬇️

With a surge in online medical advising remote monitoring of patient vitals is required. This can be facilitated with the Remote Photoplethysmography (rPPG) techniques that compute vital signs from facial videos. It involves processing video frames to obtain skin pixels, extracting the cardiac data from it and applying signal processing filters to extract the Blood Volume Pulse (BVP) signal. Different algorithms are applied to the BVP signal to estimate the various vital signs. We implemented a web application framework to measure a person's Heart Rate (HR), Heart Rate Variability (HRV), Oxygen Saturation (SpO2), Respiration Rate (RR), Blood Pressure (BP), and stress from the face video. The rPPG technique is highly sensitive to illumination and motion variation. The web application guides the users to reduce the noise due to these variations and thereby yield a cleaner BVP signal. The accuracy and robustness of the framework was validated with the help of volunteers.

91.A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective ⬇️

We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level regularization of the underlying training loss and a regularization of the first layer parameters. Similarly, our theoretical results support that the MSDA training strategy can improve adversarial robustness and generalization compared to the vanilla training strategy. Using the theoretical results, we provide a high-level understanding of how different design choices of MSDA work differently. For example, we show that the most popular MSDA methods, Mixup and CutMix, behave differently, e.g., CutMix regularizes the input gradients by pixel distances, while Mixup regularizes the input gradients regardless of pixel distances. Our theoretical results also show that the optimal MSDA strategy depends on tasks, datasets, or model parameters. From these observations, we propose generalized MSDAs, a Hybrid version of Mixup and CutMix (HMix) and Gaussian Mixup (GMix), simple extensions of Mixup and CutMix. Our implementation can leverage the advantages of Mixup and CutMix, while our implementation is very efficient, and the computation cost is almost neglectable as Mixup and CutMix. Our empirical study shows that our HMix and GMix outperform the previous state-of-the-art MSDA methods in CIFAR-100 and ImageNet classification tasks. Source code is available at this https URL

92.DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination ⬇️

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and generalization by ordering training samples in a meaningful (e.g., easy to hard) sequence. Previous work takes incorrect samples as generic hard ones without discriminating between hard samples (i.e., hard samples in correct data) and incorrect samples. Indeed, a model should learn from hard samples to promote generalization rather than overfit to incorrect ones. In this paper, we address this problem by appending a novel loss function DiscrimLoss, on top of the existing task loss. Its main effect is to automatically and stably estimate the importance of easy samples and difficult samples (including hard and incorrect samples) at the early stages of training to improve the model performance. Then, during the following stages, DiscrimLoss is dedicated to discriminating between hard and incorrect samples to improve the model generalization. Such a training strategy can be formulated dynamically in a self-supervised manner, effectively mimicking the main principle of curriculum learning. Experiments on image classification, image regression, text sequence regression, and event relation reasoning demonstrate the versatility and effectiveness of our method, particularly in the presence of diversified noise levels.

93.Forensic Dental Age Estimation Using Modified Deep Learning Neural Network ⬇️

Dental age is one of the most reliable methods to identify an individual's age. By using dental panoramic radiography (DPR) images, physicians and pathologists in forensic sciences try to establish the chronological age of individuals with no valid legal records or registered patients. The current methods in practice demand intensive labor, time, and qualified experts. The development of deep learning algorithms in the field of medical image processing has improved the sensitivity of predicting truth values while reducing the processing speed of imaging time. This study proposed an automated approach to estimate the forensic ages of individuals ranging in age from 8 to 68 using 1,332 DPR images. Initially, experimental analyses were performed with the transfer learning-based models, including InceptionV3, DenseNet201, EfficientNetB4, MobileNetV2, VGG16, and ResNet50V2; and accordingly, the best-performing model, InceptionV3, was modified, and a new neural network model was developed. Reducing the number of the parameters already available in the developed model architecture resulted in a faster and more accurate dental age estimation. The performance metrics of the results attained were as follows: mean absolute error (MAE) was 3.13, root mean square error (RMSE) was 4.77, and correlation coefficient R$^2$ was 87%. It is conceivable to propose the new model as potentially dependable and practical ancillary equipment in forensic sciences and dental medicine.

94.A Multi-Head Model for Continual Learning via Out-of-Distribution Replay ⬇️

This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of all tasks in a single head network. To prevent CF, a popular approach is to memorize a small number of samples from previous tasks and replay them during training of the new task. However, this approach still suffers from serious CF as the parameters learned for previous tasks are updated or adjusted with only the limited number of saved samples in the memory. This paper proposes an entirely different approach that builds a separate classifier (head) for each task (called a multi-head model) using a transformer network, called MORE. Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification head) without updating the network learned for previous tasks/classes. The model for the new task in MORE is trained to learn the classes of the task and also to detect samples that are not from the same data distribution (i.e., out-of-distribution (OOD)) of the task. This enables the classifier for the task to which the test instance belongs to produce a high score for the correct class and the classifiers of other tasks to produce low scores because the test instance is not from the data distributions of these classifiers. Experimental results show that MORE outperforms state-of-the-art baselines and is also naturally capable of performing OOD detection in the continual learning setting.

95.PARSE challenge 2022: Pulmonary Arteries Segmentation using Swin U-Net Transformer(Swin UNETR) and U-Net ⬇️

In this work, we present our proposed method to segment the pulmonary arteries from the CT scans using Swin UNETR and U-Net-based deep neural network architecture. Six models, three models based on Swin UNETR, and three models based on 3D U-net with residual units were ensemble using a weighted average to make the final segmentation masks. Our team achieved a multi-level dice score of 84.36 percent through this method. The code of our work is available on the following link: this https URL. This work is part of the MICCAI PARSE 2022 challenge.

96.Persuasion Strategies in Advertisements: Dataset, Modeling, and Baselines ⬇️

Modeling what makes an advertisement persuasive, i.e., eliciting the desired response from consumer, is critical to the study of propaganda, social psychology, and marketing. Despite its importance, computational modeling of persuasion in computer vision is still in its infancy, primarily due to the lack of benchmark datasets that can provide persuasion-strategy labels associated with ads. Motivated by persuasion literature in social psychology and marketing, we introduce an extensive vocabulary of persuasion strategies and build the first ad image corpus annotated with persuasion strategies. We then formulate the task of persuasion strategy prediction with multi-modal learning, where we design a multi-task attention fusion model that can leverage other ad-understanding tasks to predict persuasion strategies. Further, we conduct a real-world case study on 1600 advertising campaigns of 30 Fortune-500 companies where we use our model's predictions to analyze which strategies work with different demographics (age and gender). The dataset also provides image segmentation masks, which labels persuasion strategies in the corresponding ad images on the test split. We publicly release our code and dataset this https URL.

97.Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation ⬇️

The Solar Dynamics Observatory (SDO), a NASA multi-spectral decade-long mission that has been daily producing terabytes of observational data from the Sun, has been recently used as a use-case to demonstrate the potential of machine learning methodologies and to pave the way for future deep-space mission planning. In particular, the idea of using image-to-image translation to virtually produce extreme ultra-violet channels has been proposed in several recent studies, as a way to both enhance missions with less available channels and to alleviate the challenges due to the low downlink rate in deep space. This paper investigates the potential and the limitations of such a deep learning approach by focusing on the permutation of four channels and an encoder--decoder based architecture, with particular attention to how morphological traits and brightness of the solar surface affect the neural network predictions. In this work we want to answer the question: can synthetic images of the solar corona produced via image-to-image translation be used for scientific studies of the Sun? The analysis highlights that the neural network produces high-quality images over three orders of magnitude in count rate (pixel intensity) and can generally reproduce the covariance across channels within a 1% error. However the model performance drastically diminishes in correspondence of extremely high energetic events like flares, and we argue that the reason is related to the rareness of such events posing a challenge to model training.

98.Blind Image Deblurring with Unknown Kernel Size and Substantial Noise ⬇️

Blind image deblurring (BID) has been extensively studied in computer vision and adjacent fields. Modern methods for BID can be grouped into two categories: single-instance methods that deal with individual instances using statistical inference and numerical optimization, and data-driven methods that train deep-learning models to deblur future instances directly. Data-driven methods can be free from the difficulty in deriving accurate blur models, but are fundamentally limited by the diversity and quality of the training data -- collecting sufficiently expressive and realistic training data is a standing challenge. In this paper, we focus on single-instance methods that remain competitive and indispensable. However, most such methods do not prescribe how to deal with unknown kernel size and substantial noise, precluding practical deployment. Indeed, we show that several state-of-the-art (SOTA) single-instance methods are unstable when the kernel size is overspecified, and/or the noise level is high. On the positive side, we propose a practical BID method that is stable against both, the first of its kind. Our method builds on the recent ideas of solving inverse problems by integrating the physical models and structured deep neural networks, without extra training data. We introduce several crucial modifications to achieve the desired stability. Extensive empirical tests on standard synthetic datasets, as well as real-world NTIRE2020 and RealBlur datasets, show the superior effectiveness and practicality of our BID method compared to SOTA single-instance as well as data-driven methods. The code of our method is available at: \url{this https URL}.

99.M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval ⬇️

Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9%, 68.2%, 33.2%, 57.1%, 57.8% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.