Blue Sky Idea
in
Workshop: New Frontiers in Adversarial Machine Learning
Easy Batch Normalization
Arip Asadulaev · Alexander Panfilov · Andrey Filchenkov
Abstract:
It was shown that adversarial examples improve object recognition. But what about their opposite side, easy examples? Easy examples are samples that the machine learning model classifies correctly with high confidence. In our paper, we are making the first step toward exploring the potential benefits of using easy examples in the training procedure of neural networks. We propose to use an auxiliary batch normalization for easy examples for the standard and robust accuracy improvement.
Chat is not available.