AdvProp: One weird trick to use adversarial examples to reduce overfitting. Key idea is to use two BatchNorms, one for normal examples and another one for adversarial examples. Significant gains on ImageNet and other test sets. twitter.com/tanmingxing/st…

Many of us tried to use adversarial examples as data augmentation and observed a drop in accuracy. And it seems that simply using two BatchNorms overcomes this mysterious drop in accuracy.