AugMax: Adversarial Composition of Random Augmentations for Robust Training. (arXiv:2110.13771v3 [cs.CV] UPDATED)

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 …

arxiv cv random training