Random Erasing Data Augmentation

16 Aug 2017 Zhun Zhong Liang Zheng Guoliang Kang Shaozi Li Yi 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
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Person Re-Identification DukeMTMC-reID SVDNet + Random Erasing Rank-1 79.3 # 47
MAP 62.4 # 48
Person Re-Identification DukeMTMC-reID TriNet + Random Erasing Rank-1 73.0 # 52
MAP 56.6 # 53
Image Classification Fashion-MNIST Random Erasing Percentage error 3.65 # 3
Object Detection PASCAL VOC 2007 I+ORE MAP 76.2% # 23

Methods used in the Paper


METHOD TYPE
Random Erasing
Image Data Augmentation