Faster and Smarter AutoAugment: Augmentation Policy Search Based on Dynamic Data-Clustering

Jonghyun Bae, Ji-Hoon Kim

Keywords: Data augmentation, Image recognition, Computer vision

Abstract: Data augmentation tuned to datasets and tasks has had great success in various AI applications, such as computer vision, natural language processing, autonomous driving, and bioinformatics. However, most of the specific parameter-based augmentation strategies are inefficient in finding suitable augmentation parameters to improve the model performance whenever the dataset changes. We introduce a dynamic data augmentation strategy called Faster and Smarter AutoAugment (FSAA) that separates the data augmentation method through the initial policy search result. Based on our policy branching principle, the augmentation policy dynamically clusters data points within the dataset according to the degree of performance change at the data split stage. With extensive experimentation on various datasets for image recognition task, we show that FSAA dramatically reduces the GPU computation cost, a problem in the existing automatic data augmentation strategies, by up to over 90%. It also ensures diversity and generalization of the dataset augmentation by searching for more diverse policies than existing autonomous methods in less time, resulting in consistent performance gains and robustness across multiple models.

One-sentence Summary: Faster and Smarter AutoAugment is a dynamic data augmentation strategy that automatically searches for effective policies to improve accuracy and robustness within a short time through data clustering.

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

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