Regularization

Auxiliary Batch Normalization

Introduced by Xie et al. in Adversarial Examples Improve Image Recognition

Auxiliary Batch Normalization is a type of regularization used in adversarial training schemes. The idea is that adversarial examples should have a separate batch normalization components to the clean examples, as they have different underlying statistics.

Source: Adversarial Examples Improve Image Recognition

Papers


Paper Code Results Date Stars

Categories