Random Erasing Data Augmentation

TL;DR

Random Erasing is a simple yet effective data augmentation technique that randomly occludes parts of training images, improving CNN robustness and performance across various recognition tasks.

Contribution

The paper introduces Random Erasing, a novel data augmentation method that enhances CNN training by randomly occluding image regions, reducing overfitting and improving accuracy.

Findings

Improves image classification accuracy.

Enhances robustness to occlusion.

Complementary to existing augmentation methods.

Abstract

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Code is available at: https://github.com/zhunzhong07/Random-Erasing.