ICCV2019 Model Compression Related Works!

Model Compression Papers!!

Main Conference

Tuesday, October 29, 2019, 1030–1300 Poster 1.1 (Hall B)

12. Adversarial Robustness vs. Model Compression, or Both?  
30. HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision  

Tuesday, October 29, 2019, 1330–1530 Oral 1.2A (Hall D1) Judy Hoffman (Facebook AI Research; Georgia Tech), Min Sun (National Tsing Hua Univ.)

4.	13:48	 Searching for MobileNetV3  
5.	13:53	 Data-Free Quantization Through Weight Equalization and Bias Correction  
7.	14:06	 Knowledge Distillation via Route Constrained Optimization  
9.	14:16	 Similarity-Preserving Knowledge Distillation  

Tuesday, October 29, 2019, 1530–1800 Poster 1.2 (Hall B)

53.	15:30	 Universally Slimmable Networks and Improved Training Techniques

Wednesday, October 30, 2019, 1030–1300 Poster 2.1 (Hall B)

39.	10:30	 Accelerate CNN via Recursive Bayesian Pruning  

Thursday, October 31, 2019, 1030–1300 Poster 3.1 (Hall B)

37	10:30	 On the Efficacy of Knowledge Distillation
43	10:30	 Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
45	10:30	 Proximal Mean-Field for Neural Network Quantization
49	10:30	 Bayesian Optimized 1-Bit CNNs

Tutorials

Sat 2 Nov
Half Day AM	E5	Accelerating Computer Vision with Mixed Precision	Ming-Yu Liu(NVIDIA)

Workshops

Mon 28 Oct
Full day	308BC	Neural Architects	Samuel Albanie

ETC(Personnal Interest)

https://arxiv.org/pdf/1907.13268.pdf   
https://arxiv.org/abs/1904.02689  

[WorkShops]
Mon 28 Oct(Half day AM) 307BC Lightweight Face Recognition Challenge Jiankang Deng
Sat 02 Nov(Full day) 301 Deep Learning for Visual SLAM