Log In Sign Up

KeepAugment: A Simple Information-Preserving Data Augmentation Approach

by   Chengyue Gong, et al.

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 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.


page 2

page 4


Text Augmentation in a Multi-Task View

Traditional data augmentation aims to increase the coverage of the input...

Learning Data Augmentation Strategies for Object Detection

Data augmentation is a critical component of training deep learning mode...

Dataset Condensation with Differentiable Siamese Augmentation

In many machine learning problems, large-scale datasets have become the ...

SAGE: Saliency-Guided Mixup with Optimal Rearrangements

Data augmentation is a key element for training accurate models by reduc...

Data-Efficient Augmentation for Training Neural Networks

Data augmentation is essential to achieve state-of-the-art performance i...

Occlusions for Effective Data Augmentation in Image Classification

Deep networks for visual recognition are known to leverage "easy to reco...

Spatio-temporal Data Augmentation for Visual Surveillance

Visual surveillance aims to stably detect a foreground object using a co...