KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Authors:
- Meng LiMLMeng Li
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Circumventing Outliers of AutoAugment with Knowledge Distillation2020
- What It Thinks Is Important Is Important: Robustness Transfers Through Input Gradients2020
- Attentive Cutmix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification2020
- Shakedrop Regularization for Deep Residual LearningIEEE Access, 2019
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Deep Residual Learning for Image Recognition2016
- Scalable Person Re-identification: A Benchmark2015
- Going deeper with convolutions2015
- Microsoft COCO: Common Objects in Context2014
- Saliency Detection: A Boolean Map Approach2013