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
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 28 in the graph, strongest link: official). This answer is about arXiv:1708.04552, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1708.04552 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified (of 24 harvested samples) · 5 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 64 · with a code link: 43 · where Syntology ran a sample: 18 (17 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (18 of 64 tagged: 17 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 64 of 64, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
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 official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 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 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples)
-
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
-
KeepAugment: A Simple Information-Preserving Data Augmentation Approach 23 Nov 2020 · 1 repository · arXiv:2011.11778
-
Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients 11 Nov 2020 · 1 repository · arXiv:2011.05649
-
Deep Active Learning with Augmentation-based Consistency Estimation 5 Nov 2020 · 1 repository · arXiv:2011.02666
-
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians 26 Oct 2020 · 1 repository · arXiv:2010.13514Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
Improving Generalization in Reinforcement Learning with Mixture Regularization 21 Oct 2020 · 2 repositories · arXiv:2010.10814
-
How Does Supernet Help in Neural Architecture Search? 16 Oct 2020 · 0 repositories · arXiv:2010.08219
-
Regularizing Neural Networks via Adversarial Model Perturbation 10 Oct 2020 · 1 repository · arXiv:2010.04925Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples)
-
MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values 27 Jul 2020 · 2 repositories · arXiv:2007.13723
-
SSN: Soft Shadow Network for Image Compositing 16 Jul 2020 · 1 repository · arXiv:2007.08211
-
RobFR: Benchmarking Adversarial Robustness on Face Recognition 8 Jul 2020 · 2 repositories · arXiv:2007.04118Syntology official (archive's flag): 6 ran · 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 23 harvested samples)
-
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 · 13 repositories · arXiv:2006.10738Syntology official (archive's flag): 7 ran · 49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified (of 58 harvested samples) · 15 pointer-only (licence)
-
Angle-based Search Space Shrinking for Neural Architecture Search 28 Apr 2020 · 1 repository · arXiv:2004.13431Syntology 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 1 pointer-only (licence)
-
ResNeSt: Split-Attention Networks 19 Apr 2020 · 36 repositories · arXiv:2004.08955Syntology official (archive's flag): 5 ran · 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified (of 48 harvested samples) · 23 pointer-only (licence)
-
How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference 30 Mar 2020 · 1 repository · arXiv:2003.13593
-
TResNet: High Performance GPU-Dedicated Architecture 30 Mar 2020 · 3 repositories · arXiv:2003.13630
-
Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification 29 Mar 2020 · 1 repository · arXiv:2003.13048
-
Getting to 99% Accuracy in Interactive Segmentation 17 Mar 2020 · 3 repositories · arXiv:2003.07932
-
Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition 6 Mar 2020 · 1 repository · arXiv:2003.03206
-
Data augmentation with Mobius transformations 7 Feb 2020 · 1 repository · arXiv:2002.02917
-
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network 17 Jan 2020 · 1 repository · arXiv:2001.06268Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified (of 11 harvested samples)
-
UNAS: Differentiable Architecture Search Meets Reinforcement Learning 16 Dec 2019 · 1 repository · arXiv:1912.07651
-
Neural Predictor for Neural Architecture Search 2 Dec 2019 · 2 repositories · arXiv:1912.00848Syntology 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples)
-
Adversarial Examples Improve Image Recognition 21 Nov 2019 · 6 repositories · arXiv:1911.09665Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
RandAugment: Practical automated data augmentation with a reduced search space 30 Sep 2019 · 19 repositories · arXiv:1909.13719Syntology 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified (of 65 harvested samples) · 17 pointer-only (licence)
-
Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing 1 Sep 2019 · 1 repository · arXiv:1909.00390
-
SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search 16 Aug 2019 · 1 repository · arXiv:1908.06022
-
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation 6 Jun 2019 · 2 repositories · arXiv:1906.02611Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Semi-supervised semantic segmentation needs strong, varied perturbations 5 Jun 2019 · 5 repositories · arXiv:1906.01916Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)
-
Fast AutoAugment 1 May 2019 · 11 repositories · arXiv:1905.00397Syntology official (archive's flag): 9 ran · 37 ran (of which 2 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 0 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 3 unverified (of 40 harvested samples) · 7 pointer-only (licence)
-
MultiGrain: a unified image embedding for classes and instances 14 Feb 2019 · 3 repositories · arXiv:1902.05509Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware 2 Dec 2018 · 23 repositories · arXiv:1812.00332Syntology official (archive's flag): 2 ran · 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified (of 27 harvested samples) · 4 pointer-only (licence)
-
Data Augmentation using Random Image Cropping and Patching for Deep CNNs 22 Nov 2018 · 1 repository · arXiv:1811.09030
-
DropFilter: A Novel Regularization Method for Learning Convolutional Neural Networks 16 Nov 2018 · 0 repositories · arXiv:1811.06783
-
Improved Regularization of Convolutional Neural Networks with Cutout 15 Aug 2017 · 28 repositories · arXiv:1708.04552Syntology community repositories only · 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified (of 24 harvested samples) · 5 pointer-only (licence)
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