WeMix: How to Better Utilize Data Augmentation

Yi Xu, Asaf Noy, Ming Lin, Qi Qian, Li Hao, Rong Jin

Keywords: Data Augmentation, Data Bias, Non-convex Optimization, Deep Learning Theory

Abstract: Data augmentation is a widely used training trick in deep learning to improve the network generalization ability. Despite many encouraging results, several recent studies did point out limitations of the conventional data augmentation scheme in certain scenarios, calling for a better theoretical understanding of data augmentation. In this work, we develop a comprehensive analysis that reveals pros and cons of data augmentation. The main limitation of data augmentation arises from the data bias, i.e. the augmented data distribution can be quite different from the original one. This data bias leads to a suboptimal performance of existing data augmentation methods. To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation. Our theoretical analysis shows that both algorithms are guaranteed to improve the effect of data augmentation through the bias correction, which is further validated by our empirical studies. Finally, we propose a generic algorithm "WeMix" by combining AugDrop and MixLoss, whose effectiveness is observed from extensive empirical evaluations.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: This paper theoretically and empirically studies how to better utilize data augmentation by correcting data bias.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=LfFkAFttU1