🔭 I’m working on computer vision, with a particular focus on investigating the internal representations of deep neural networks, improving their training dynamics, evaluating their robustness, and delving into their generalization abilities.
Highlights
- Pro
Pinned Loading
-
visualkeras
visualkeras PublicVisualkeras is a Python package to help visualize Keras (either standalone or included in TensorFlow) neural network architectures. It allows easy styling to fit most needs. This module supports la…
-
CNN-Filter-DB
CNN-Filter-DB PublicA database of over 1.4 billion 3x3 convolution filters extracted from hundreds of diverse CNN models with relevant meta information (CVPR 2022 ORAL)
-
cvpr22w_RobustnessThroughTheLens
cvpr22w_RobustnessThroughTheLens PublicOfficial repository of our submission "Adversarial Robustness through the Lens of Convolutional Filters" for the CVPR2022 Workshop "The Art of Robustness: Devil and Angel in Adversarial Machine Lea…
Jupyter Notebook 8
-
tinytorchtrainer
tinytorchtrainer PublicA small framework to train image classifiers in PyTorch
Python 4
-
vlm_shapebias
vlm_shapebias PublicOfficial code for "Are Vision Language Models Texture or Shape Biased and Can We Steer Them?".
Python 13
-
biases_vs_generalization
biases_vs_generalization PublicOfficial code for the CVPR 2024 Paper "Can Biases in ImageNet Models Explain Generalization?".
If the problem persists, check the GitHub status page or contact support.