Random Erasing Data Augmentation

TLDR

The paper proposes Random Erasing, a novel data augmentation technique for training CNNs. Random Erasing works by randomly selecting a rectangular region in an image and filling it with random pixel values. The method reduces over‑fitting, improves robustness to occlusion, is parameter‑free and easy to integrate, and consistently outperforms strong baselines across image classification, object detection, and person re‑identification. Code is available at https://github.com/zhunzhong07/Random-Erasing.

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.