TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Cutout

Cutout

Computer VisionIntroduced 200064 papers
Source Paper

Description

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, tracking, 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

Papers Using This Method

Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation2025-01-15Provable Benefit of Cutout and CutMix for Feature Learning2024-10-31Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions2024-09-26Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization2024-07-11Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation2024-03-22DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition2024-01-01TextAug: Test time Text Augmentation for Multimodal Person Re-identification2023-12-04NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation2023-11-20Studying the Impact of Augmentations on Medical Confidence Calibration2023-08-23Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches2023-06-22PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing2023-02-28Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge2023-01-24NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension2022-11-23Feature Weaken: Vicinal Data Augmentation for Classification2022-11-20Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace2022-08-11ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation2022-06-05Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification2022-06-05AGNAS: Attention-Guided Micro- and Macro-Architecture Search2022-06-05CNNs Avoid Curse of Dimensionality by Learning on Patches2022-05-22Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging2022-04-22