Timezone: »

 
Poster
AugMax: Adversarial Composition of Random Augmentations for Robust Training
Haotao Wang · Chaowei Xiao · Jean Kossaifi · Zhiding Yu · Anima Anandkumar · Zhangyang Wang

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @ Virtual
in Poster Session 2 »

Data augmentation is a simple yet effective way to improve the robustness of deep neural networks (DNNs). Diversity and hardness are two complementary dimensions of data augmentation to achieve robustness. For example, AugMix explores random compositions of a diverse set of augmentations to enhance broader coverage, while adversarial training generates adversarially hard samples to spot the weakness. Motivated by this, we propose a data augmentation framework, termed AugMax, to unify the two aspects of diversity and hardness. AugMax first randomly samples multiple augmentation operators and then learns an adversarial mixture of the selected operators. Being a stronger form of data augmentation, AugMax leads to a significantly augmented input distribution which makes model training more challenging. To solve this problem, we further design a disentangled normalization module, termed DuBIN (Dual-Batch-and-Instance Normalization), that disentangles the instance-wise feature heterogeneity arising from AugMax. Experiments show that AugMax-DuBIN leads to significantly improved out-of-distribution robustness, outperforming prior arts by 3.03%, 3.49%, 1.82% and 0.71% on CIFAR10-C, CIFAR100-C, Tiny ImageNet-C and ImageNet-C. Codes and pretrained models are available: https://github.com/VITA-Group/AugMax.

Keywords: Deep Learning · Robustness · Adversarial Robustness and Security

Author Information

Haotao Wang (University of Texas at Austin)
Chaowei Xiao (University of Michigan, Ann Arbor)

I am Chaowei Xiao, a third year PhD student in CSE Department, University of Michigan, Ann Arbor. My advisor is Professor Mingyan Liu . I obtained my bachelor's degree in School of Software from Tsinghua University in 2015, advised by Professor Yunhao Liu, Professor Zheng Yang and Dr. Lei Yang. I was also a visiting student at UC Berkeley in 2018, advised by Professor Dawn Song and Professor Bo Li. My research interest includes adversarial machine learning.

Jean Kossaifi (NVIDIA Research)
Zhiding Yu (NVIDIA)
Anima Anandkumar (NVIDIA/Caltech)
Zhangyang Wang (UT Austin)

More from the Same Authors