Papers › Random Erasing Data Augmentation
Random Erasing Data Augmentation
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. 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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
18 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | Fashion-MNIST | Random Erasing | Percentage error | 3.65 | #2 of 34 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 | I+ORE | MAP | 76.2% | #18 of 30 | Archive leaderboard | report |
| Person Re-Identification | DukeMTMC-reID | SVDNet + Random Erasing | Rank-1 | 79.3 | #72 of 94 | Archive leaderboard | report |
| Person Re-Identification | DukeMTMC-reID | SVDNet + Random Erasing | mAP | 62.4 | #72 of 94 | Archive leaderboard | report |
| Person Re-Identification | DukeMTMC-reID | TriNet + Random Erasing | Rank-1 | 73.0 | #77 of 94 | Archive leaderboard | report |
| Person Re-Identification | DukeMTMC-reID | TriNet + Random Erasing | mAP | 56.6 | #77 of 94 | Archive leaderboard | report |
| Robust Object Detection | Cityscapes | Cutout | mPC [AP] | 15.7 | #12 of 13 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: Random Erasing
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections