Methods › Computer Vision › Image Data Augmentation › Random Erasing
Random Erasing
Introduced by Zhun Zhong et al. in Random Erasing Data Augmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Random Erasing is a data augmentation method for training the convolutional neural network (CNN), which 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. Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and can be implemented in various vision tasks, such as image classification, object detection, semantic segmentation.
In the Albumentations library, there is a generalization of RandomErasing called CoarseDropout, which allows masking an arbitrary number of regions of rectangular shape.
It could be applied to images, segmentation masks, and key points.
Papers archive 2025-07-28
19 shown of 19, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Data Augmentation Through Random Style Replacement 14 Apr 2025 · 0 repositories · arXiv:2504.10563
-
Learning to Learn Transferable Generative Attack for Person Re-Identification 6 Sep 2024 · 0 repositories · arXiv:2409.04208
-
Defending against Model Inversion Attacks via Random Erasing 2 Sep 2024 · 0 repositories · arXiv:2409.01062
-
Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge Distillation 28 Jul 2024 · 1 repository · arXiv:2407.19540
-
Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery 27 Jul 2024 · 0 repositories · arXiv:2407.19184
-
Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification 8 Jan 2024 · 0 repositories · arXiv:2401.03912
-
Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models 28 Oct 2023 · 0 repositories · arXiv:2310.18850
-
Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis 1 Aug 2023 · 0 repositories · arXiv:2308.00323
-
Masking meets Supervision: A Strong Learning Alliance 20 Jun 2023 · 1 repository · arXiv:2306.11339
-
Learning to Disentangle Scenes for Person Re-identification 10 Nov 2021 · 1 repository · arXiv:2111.05476
-
Benchmarks for Corruption Invariant Person Re-identification 1 Nov 2021 · 1 repository · arXiv:2111.00880Syntology ran 2 of 2 samples · 0 unverified
-
Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning 29 Sep 2021 · 0 repositories
-
Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network 2 Apr 2021 · 1 repository · arXiv:2104.01032
-
Improved Meta-Learning Training for Speaker Verification 29 Mar 2021 · 0 repositories · arXiv:2103.15421
-
Channel Augmented Joint Learning for Visible-Infrared Recognition 1 Jan 2021 · 3 repositories
-
Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks 9 Nov 2020 · 0 repositories · arXiv:2011.04121
-
Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition 26 Aug 2020 · 0 repositories · arXiv:2008.11401
-
Data Augmentation for Skin Lesion Analysis 5 Sep 2018 · 1 repository · arXiv:1809.01442Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
Random Erasing Data Augmentation 16 Aug 2017 · 18 repositories · arXiv:1708.04896
Tasks archive 2025-07-28
20 shown of 43 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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