Random Erasing Data Augmentation

16 Aug 2017Zhun ZhongLiang ZhengGuoliang KangShaozi LiYi Yang

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... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Person Re-Identification DukeMTMC-reID SVDNet + Random Erasing Rank-1 79.3 # 6
Person Re-Identification DukeMTMC-reID SVDNet + Random Erasing MAP 62.4 # 5
Person Re-Identification DukeMTMC-reID TriNet + Random Erasing Rank-1 73.0 # 10
Person Re-Identification DukeMTMC-reID TriNet + Random Erasing MAP 56.6 # 9
Image Classification Fashion-MNIST Random Erasing Percentage error 3.65 # 1
Object Detection PASCAL VOC 2007 I+ORE MAP 76.2% # 11