{"url":"/method/random-erasing","slug":"random-erasing","name":"Random Erasing","full_name":"Random Erasing","full_name_withheld":false,"description_markdown":"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.\r\n\r\nIn the [Albumentations](https://albumentations.ai/) library, there is a generalization of RandomErasing called [CoarseDropout](https://albumentations.ai/docs/api_reference/augmentations/dropout/coarse_dropout/?h=coa#albumentations.augmentations.dropout.coarse_dropout.CoarseDropout), which allows masking an arbitrary number of regions of rectangular shape.\r\n\r\nIt could be applied to images, segmentation masks, and key points.\r\n\r\n[Documentation for CoarseDropout](https://albumentations.ai/docs/api_reference/augmentations/dropout/coarse_dropout/?h=coa#albumentations.augmentations.dropout.coarse_dropout.CoarseDropout)","description_state":"present","introduced_year":null,"introduced_by":{"title":"Random Erasing Data Augmentation","paper":"/paper/random-erasing-data-augmentation","first_author":"Zhun Zhong","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/random-erasing-data-augmentation"},"source":{"url":"http://arxiv.org/abs/1708.04896v2","title":"Random Erasing Data Augmentation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/zhunzhong07/Random-Erasing","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Data Augmentation","url":"/methods/category/image-data-augmentation","pwc_aliases":[]}],"n_papers_tagged":19,"archive_num_papers":19,"papers_newest_first":[{"paper":null,"title":"Data Augmentation Through Random Style Replacement","date":"2025-04-14","arxiv_id":"2504.10563","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning to Learn Transferable Generative Attack for Person Re-Identification","date":"2024-09-06","arxiv_id":"2409.04208","n_code_links":0,"syntology":null},{"paper":null,"title":"Defending against Model Inversion Attacks via Random Erasing","date":"2024-09-02","arxiv_id":"2409.01062","n_code_links":0,"syntology":null},{"paper":"/paper/overcoming-uncertain-incompleteness-for","title":"Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge Distillation","date":"2024-07-28","arxiv_id":"2407.19540","n_code_links":1,"syntology":null},{"paper":null,"title":"Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery","date":"2024-07-27","arxiv_id":"2407.19184","n_code_links":0,"syntology":null},{"paper":null,"title":"Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification","date":"2024-01-08","arxiv_id":"2401.03912","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models","date":"2023-10-28","arxiv_id":"2310.18850","n_code_links":0,"syntology":null},{"paper":null,"title":"Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis","date":"2023-08-01","arxiv_id":"2308.00323","n_code_links":0,"syntology":null},{"paper":"/paper/augmenting-sub-model-to-improve-main-model","title":"Masking meets Supervision: A Strong Learning Alliance","date":"2023-06-20","arxiv_id":"2306.11339","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-disentangle-scenes-for-person-re","title":"Learning to Disentangle Scenes for Person Re-identification","date":"2021-11-10","arxiv_id":"2111.05476","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarks-for-corruption-invariant-person-re","title":"Benchmarks for Corruption Invariant Person Re-identification","date":"2021-11-01","arxiv_id":"2111.00880","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/plot2api-recommending-graphic-api-from-plot","title":"Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network","date":"2021-04-02","arxiv_id":"2104.01032","n_code_links":1,"syntology":null},{"paper":null,"title":"Improved Meta-Learning Training for Speaker Verification","date":"2021-03-29","arxiv_id":"2103.15421","n_code_links":0,"syntology":null},{"paper":"/paper/channel-augmented-joint-learning-for-visible","title":"Channel Augmented Joint Learning for Visible-Infrared Recognition","date":"2021-01-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":null,"title":"Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks","date":"2020-11-09","arxiv_id":"2011.04121","n_code_links":0,"syntology":null},{"paper":null,"title":"Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition","date":"2020-08-26","arxiv_id":"2008.11401","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-for-skin-lesion-analysis","title":"Data Augmentation for Skin Lesion Analysis","date":"2018-09-05","arxiv_id":"1809.01442","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":"/paper/random-erasing-data-augmentation","title":"Random Erasing Data Augmentation","date":"2017-08-16","arxiv_id":"1708.04896","n_code_links":18,"syntology":null}],"papers_shown":19,"tasks":[{"task":"/task/data-augmentation","name":"Data Augmentation","papers":12},{"task":"/task/image-classification","name":"Image Classification","papers":5},{"task":"/task/person-re-identification","name":"Person Re-Identification","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":4},{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/classification","name":"General Classification","papers":2},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":2},{"task":"/task/meta-learning","name":"Meta-Learning","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/cross-view-person-re-identification","name":"Cross-Modal Person Re-Identification","papers":1},{"task":"/task/data-visualization","name":"Data Visualization","papers":1},{"task":"/task/facial-expression-recognition-1","name":"Facial Expression Recognition","papers":1},{"task":"/task/facial-expression-recognition","name":"Facial Expression Recognition (FER)","papers":1},{"task":"/task/fine-grained-image-classification","name":"Fine-Grained Image Classification","papers":1},{"task":"/task/fire-detection","name":"Fire Detection","papers":1},{"task":"/task/generalizable-person-re-identification","name":"Generalizable Person Re-identification","papers":1}],"tasks_shown":20,"n_tasks":43,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":1},{"year":"2020","papers":2},{"year":"2021","papers":6},{"year":"2023","papers":3},{"year":"2024","papers":5},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/random-erasing"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}