Viet-Anh on Software Logo

What is: Auxiliary Batch Normalization?

SourceAdversarial Examples Improve Image Recognition
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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.