Random Erasing Data Augmentation

Zhun Zhong; Liang Zheng; Guoliang Kang; Shaozi Li; Yi Yang

doi:10.1609/aaai.v34i07.7000

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.

Keywords

Random forestComputer scienceArtificial intelligenceConvolutional neural networkRectanglePixelIdentification (biology)Image (mathematics)Pattern recognition (psychology)Code (set theory)Convolution random number generatorProcess (computing)Object (grammar)Random functionAlgorithmRandom variableMathematicsStatisticsProgramming language

Affiliated Institutions

Related Publications

A survey on Image Data Augmentation for Deep Learning

Connor Shorten , Taghi M. Khoshgoftaar

Abstract Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfi...

2019 Journal Of Big Data 11041 citations

Data augmentation for improving deep learning in image classification problem

Agnieszka Mikołajczyk , Michał Grochowski

These days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neura...

2018 2018 International Interdisciplinary ... 1623 citations

Albumentations: Fast and Flexible Image Augmentations

Alexander Buslaev , Vladimir I. Iglovikov , Eugene Khvedchenya +3 more

Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve correspo...

2020 Information 1852 citations

TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks

Dmitry Laptev , Nikolay Savinov , Joachim M. Buhmann +1 more

In this paper we present a deep neural network topology that incorporates a simple to implement transformationinvariant pooling operator (TI-POOLING). This operator is able to e...

2016 250 citations

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Ross Girshick , Jeff Donahue , Trevor Darrell +1 more

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that...

2014 30615 citations

Publication Info

Year: 2020
Type: article
Volume: 34
Issue: 07
Pages: 13001-13008
Citations: 2689
Access: Closed

External Links

Download PDF (Free) View on DOI.org arXiv Semantic Scholar

Social Impact

Altmetric

Random Erasing Data Augmentation

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

2689

OpenAlex

285

Influential

1931

CrossRef

Cite This

APA Style

                            
                                
                                    Zhun Zhong, 
                                
                                    Liang Zheng, 
                                
                                    Guoliang Kang
                                
                                et al.
                            
                            (2020). 
                            Random Erasing Data Augmentation. 
                            Proceedings of the AAAI Conference on Artificial Intelligence
                            , 34
                            (07)
                            , 13001-13008.
                            https://doi.org/10.1609/aaai.v34i07.7000
                        

Identifiers

DOI: 10.1609/aaai.v34i07.7000
arXiv: 1708.04896

Data Quality

Data completeness: 84%