{"url":"/method/cutout","slug":"cutout","name":"Cutout","full_name":"Cutout","full_name_withheld":false,"description_markdown":"**Cutout** is an image augmentation and regularization technique that randomly masks out square regions of input during training. and can be used to improve the robustness and overall performance of convolutional neural networks. The main motivation for cutout comes from the problem of object occlusion, which is commonly encountered in many computer vision tasks, such as object recognition,\r\ntracking, or human pose estimation. By generating new images which simulate occluded examples, we not only better prepare the model for encounters with occlusions in the real world, but the model also learns to take more of the image context into consideration when making decisions","description_state":"present","introduced_year":null,"introduced_by":{"title":"Improved Regularization of Convolutional Neural Networks with Cutout","paper":"/paper/improved-regularization-of-convolutional","first_author":"Terrance DeVries","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/improved-regularization-of-convolutional"},"source":{"url":"http://arxiv.org/abs/1708.04552v2","title":"Improved Regularization of Convolutional Neural Networks with Cutout","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Data Augmentation","url":"/methods/category/image-data-augmentation","pwc_aliases":[]}],"n_papers_tagged":64,"archive_num_papers":64,"papers_newest_first":[{"paper":"/paper/mantis-shrimp-exploring-photometric-band","title":"Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation","date":"2025-01-15","arxiv_id":"2501.09112","n_code_links":1,"syntology":null},{"paper":null,"title":"Provable Benefit of Cutout and CutMix for Feature Learning","date":"2024-10-31","arxiv_id":"2410.23672","n_code_links":0,"syntology":null},{"paper":null,"title":"Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions","date":"2024-09-26","arxiv_id":"2409.18228","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization","date":"2024-07-11","arxiv_id":"2407.08374","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation","date":"2024-03-22","arxiv_id":"2403.15512","n_code_links":0,"syntology":null},{"paper":null,"title":"DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition","date":"2024-01-01","arxiv_id":"2401.01387","n_code_links":0,"syntology":null},{"paper":null,"title":"TextAug: Test time Text Augmentation for Multimodal Person Re-identification","date":"2023-12-04","arxiv_id":"2312.01605","n_code_links":0,"syntology":null},{"paper":"/paper/nng-mix-improving-semi-supervised-anomaly","title":"NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation","date":"2023-11-20","arxiv_id":"2311.11961","n_code_links":1,"syntology":null},{"paper":null,"title":"Studying the Impact of Augmentations on Medical Confidence Calibration","date":"2023-08-23","arxiv_id":"2308.11902","n_code_links":0,"syntology":null},{"paper":null,"title":"Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches","date":"2023-06-22","arxiv_id":"2306.12610","n_code_links":0,"syntology":null},{"paper":null,"title":"PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing","date":"2023-02-28","arxiv_id":"2303.00137","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-neural-architecture-search-for","title":"Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge","date":"2023-01-24","arxiv_id":"2301.10281","n_code_links":1,"syntology":null},{"paper":"/paper/nas-lid-efficient-neural-architecture-search","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","date":"2022-11-23","arxiv_id":"2211.12759","n_code_links":1,"syntology":null},{"paper":null,"title":"Feature Weaken: Vicinal Data Augmentation for Classification","date":"2022-11-20","arxiv_id":"2211.10944","n_code_links":0,"syntology":null},{"paper":"/paper/regularizing-deep-neural-networks-with-1","title":"Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace","date":"2022-08-11","arxiv_id":"2208.05924","n_code_links":1,"syntology":{"ran":4,"of":5,"unverified":1,"pointer_only":5}},{"paper":"/paper/agnas-attention-guided-micro-and-macro","title":"AGNAS: Attention-Guided Micro- and Macro-Architecture Search","date":"2022-06-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification","date":"2022-06-05","arxiv_id":"2206.02098","n_code_links":0,"syntology":null},{"paper":"/paper/shapepu-a-new-pu-learning-framework","title":"ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation","date":"2022-06-05","arxiv_id":"2206.02118","n_code_links":1,"syntology":null},{"paper":null,"title":"CNNs Avoid Curse of Dimensionality by Learning on Patches","date":"2022-05-22","arxiv_id":"2205.10760","n_code_links":0,"syntology":null},{"paper":null,"title":"Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging","date":"2022-04-22","arxiv_id":"2204.10846","n_code_links":0,"syntology":null},{"paper":"/paper/generalizing-few-shot-nas-with-gradient-1","title":"Generalizing Few-Shot NAS with Gradient Matching","date":"2022-03-29","arxiv_id":"2203.15207","n_code_links":1,"syntology":{"ran":0,"of":7,"unverified":7,"pointer_only":0}},{"paper":null,"title":"Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search","date":"2022-02-23","arxiv_id":"2202.11490","n_code_links":0,"syntology":null},{"paper":null,"title":"Data-Free Neural Architecture Search via Recursive Label Calibration","date":"2021-12-03","arxiv_id":"2112.02086","n_code_links":0,"syntology":null},{"paper":"/paper/profiling-neural-blocks-and-design-spaces-for","title":"Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search","date":"2021-09-25","arxiv_id":"2109.12426","n_code_links":1,"syntology":null},{"paper":null,"title":"Federated Model Search via Reinforcement Learning","date":"2021-07-07","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Free-Text Keystroke Dynamics for User Authentication","date":"2021-07-01","arxiv_id":"2107.07009","n_code_links":0,"syntology":null},{"paper":null,"title":"Generative Adversarial Neural Architecture Search","date":"2021-05-19","arxiv_id":"2105.09356","n_code_links":0,"syntology":null},{"paper":null,"title":"DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning","date":"2021-02-25","arxiv_id":"2102.13123","n_code_links":0,"syntology":null},{"paper":"/paper/convnets-for-counting-object-detection-of","title":"ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums","date":"2021-02-01","arxiv_id":"2102.00632","n_code_links":1,"syntology":null},{"paper":"/paper/generalized-latency-performance-estimation","title":"Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search","date":"2021-01-04","arxiv_id":"2101.00732","n_code_links":2,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":22},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":19},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":17},{"task":"/task/image-classification","name":"image-classification","papers":13},{"task":"/task/object-detection","name":"Object Detection","papers":7},{"task":null,"name":"GPU","papers":6},{"task":"/task/classification","name":"General Classification","papers":6},{"task":"/task/object-detection-1","name":"object-detection","papers":6},{"task":"/task/domain-generalization","name":"Domain Generalization","papers":4},{"task":"/task/image-augmentation","name":"Image Augmentation","papers":4},{"task":"/task/diversity","name":"Diversity","papers":3},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":3},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":3},{"task":"/task/retrieval","name":"Retrieval","papers":3},{"task":"/task/segmentation","name":"Segmentation","papers":3},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":3},{"task":"/task/classification-1","name":"Classification","papers":2},{"task":"/task/deep-learning","name":"Deep Learning","papers":2}],"tasks_shown":20,"n_tasks":94,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":3},{"year":"2019","papers":10},{"year":"2020","papers":20},{"year":"2021","papers":8},{"year":"2022","papers":10},{"year":"2023","papers":6},{"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/cutout"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}