# WeMix: How to Better Utilize Data Augmentation

arXiv: https://arxiv.org/abs/2010.01267 · HTML: https://mlsanity.com/paper/2010.01267/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [The Effects of Regularization and Data Augmentation are Class Dependent](https://mlsanity.com/paper/2204.03632/) (2022)
- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [Resilient Constrained Learning](https://mlsanity.com/paper/2306.02426/) (2023)
- [Understanding the Detrimental Class-level Effects of Data Augmentation](https://mlsanity.com/paper/2401.01764/) (2023)
- [Automated Semiconductor Defect Inspection in Scanning Electron Microscope Images: a Systematic Review](https://mlsanity.com/paper/2308.08376/) (2023)
- [A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit](https://mlsanity.com/paper/2303.00510/) (2023)
- [Context Normalization Layer with Applications](https://mlsanity.com/paper/2303.07651/) (2023)
- [The geometry of invariant learning: an information-theoretic analysis of data augmentation and generalization](https://mlsanity.com/paper/2602.14423/) (2026)

## Abstract (arXiv)

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.