KeepAugment: A Simple Information-Preserving Data Augmentation Approach
This work addresses the problem of noisy augmented data for deep learning practitioners, offering a method to improve the fidelity of augmented images.
The paper identifies that data augmentation can introduce noisy examples, hurting performance. They propose KeepAugment, which uses saliency maps to preserve important regions during augmentation, leading to more faithful training examples.
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on unaugmented data during inference. To alleviate this issue, we propose a simple yet highly effective approach, dubbed \emph{KeepAugment}, to increase augmented images fidelity. The idea is first to use the saliency map to detect important regions on the original images and then preserve these informative regions during augmentation. This information-preserving strategy allows us to generate more faithful training examples. Empirically, we demonstrate our method significantly improves on a number of prior art data augmentation schemes, e.g. AutoAugment, Cutout, random erasing, achieving promising results on image classification, semi-supervised image classification, multi-view multi-camera tracking and object detection.