Methods › Computer Vision › Image Data Augmentation › Cutout
Cutout
Introduced by Terrance DeVries et al. in Improved Regularization of Convolutional Neural Networks with Cutout
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 archive 2025-07-28
30 shown of 64, 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.
-
Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation 15 Jan 2025 · 1 repository · arXiv:2501.09112
-
Provable Benefit of Cutout and CutMix for Feature Learning 31 Oct 2024 · 0 repositories · arXiv:2410.23672
-
Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions 26 Sep 2024 · 0 repositories · arXiv:2409.18228
-
Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization 11 Jul 2024 · 0 repositories · arXiv:2407.08374
-
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation 22 Mar 2024 · 0 repositories · arXiv:2403.15512
-
DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition 1 Jan 2024 · 0 repositories · arXiv:2401.01387
-
TextAug: Test time Text Augmentation for Multimodal Person Re-identification 4 Dec 2023 · 0 repositories · arXiv:2312.01605
-
NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation 20 Nov 2023 · 1 repository · arXiv:2311.11961
-
Studying the Impact of Augmentations on Medical Confidence Calibration 23 Aug 2023 · 0 repositories · arXiv:2308.11902
-
Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches 22 Jun 2023 · 0 repositories · arXiv:2306.12610
-
PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing 28 Feb 2023 · 0 repositories · arXiv:2303.00137
-
Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge 24 Jan 2023 · 1 repository · arXiv:2301.10281
-
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension 23 Nov 2022 · 1 repository · arXiv:2211.12759
-
Feature Weaken: Vicinal Data Augmentation for Classification 20 Nov 2022 · 0 repositories · arXiv:2211.10944
-
Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace 11 Aug 2022 · 1 repository · arXiv:2208.05924Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
-
AGNAS: Attention-Guided Micro- and Macro-Architecture Search 5 Jun 2022 · 1 repository
-
Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification 5 Jun 2022 · 0 repositories · arXiv:2206.02098
-
ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation 5 Jun 2022 · 1 repository · arXiv:2206.02118
-
CNNs Avoid Curse of Dimensionality by Learning on Patches 22 May 2022 · 0 repositories · arXiv:2205.10760
-
Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging 22 Apr 2022 · 0 repositories · arXiv:2204.10846
-
Generalizing Few-Shot NAS with Gradient Matching 29 Mar 2022 · 1 repository · arXiv:2203.15207Syntology ran 0 of 7 samples · 7 unverified
-
Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search 23 Feb 2022 · 0 repositories · arXiv:2202.11490
-
Data-Free Neural Architecture Search via Recursive Label Calibration 3 Dec 2021 · 0 repositories · arXiv:2112.02086
-
Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search 25 Sep 2021 · 1 repository · arXiv:2109.12426
-
Federated Model Search via Reinforcement Learning 7 Jul 2021 · 0 repositories
-
Free-Text Keystroke Dynamics for User Authentication 1 Jul 2021 · 0 repositories · arXiv:2107.07009
-
Generative Adversarial Neural Architecture Search 19 May 2021 · 0 repositories · arXiv:2105.09356
-
DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning 25 Feb 2021 · 0 repositories · arXiv:2102.13123
-
ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums 1 Feb 2021 · 1 repository · arXiv:2102.00632
-
Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search 4 Jan 2021 · 2 repositories · arXiv:2101.00732
Tasks archive 2025-07-28
20 shown of 94 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