Random Erasing Data Augmentation

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.

References in corpus (3)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Person Re-identification: Past, Present and Future
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks

Cited by in corpus (6)

• Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
• Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
• The Herbarium Challenge 2019 Dataset
• XNAS: Neural Architecture Search with Expert Advice
• A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
• Automated Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction