mlsanityData to 7 Oct 2026

Improved Regularization of Convolutional Neural Networks with Cutout

arXiv 1708.04552 ↗First posted 15 Aug 2017cs.CVcited by 1,623

Not on the map. Why?

Cited by 39 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks. However, due to the model capacity required to capture such representations, they are often susceptible to overfitting and therefore require proper regularization in order to generalize well. In this paper, we show that the simple regularization technique of randomly masking out square regions of input during training, which we call cutout, can be used to improve the robustness and overall performance of convolutional neural networks. Not only is this method extremely easy to implement, but we also demonstrate that it can be used in conjunction with existing forms of data augmentation and other regularizers to further improve model performance. We evaluate this method by applying it to current state-of-the-art architectures on the CIFAR-10, CIFAR-100, and SVHN datasets, yielding new state-of-the-art results of 2.56%, 15.20%, and 1.30% test error respectively. Code is available at https://github.com/uoguelph-mlrg/Cutout

Key facts. Cited by 1,623 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 343; 2022: 350; 2023: 362; 2024: 286; 2025: 183; 2026: 98.

1,623 papers.

Sort:

By area:

  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2021Robust fine-tuning of zero-shot modelscited by 785
  4. 2021Domain Generalization: A Surveycited by 760
  5. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  6. 2021ImageNet-21K Pretraining for the Massescited by 607
  7. 2021Domain Generalization with MixStylecited by 563
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  9. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  10. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  11. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  12. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
38 more
  1. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 307
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  3. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  4. 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
  5. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 290
  6. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  7. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  8. 2021A Survey on Deep Semi-supervised Learningcited by 250
  9. 2021Improving Robustness using Generated Datacited by 233
  10. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
  11. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  12. 2021Parametric Contrastive Learningcited by 217
  13. 2021Vision Transformers are Robust Learnerscited by 208
  14. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  15. 2021R-Drop: Regularized Dropout for Neural Networkscited by 202
  16. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  17. 2021Data Augmentation Can Improve Robustnesscited by 193
  18. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  19. 2022Datamodels: Predicting Predictions from Training Datacited by 186
  20. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  21. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  22. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 177
  23. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  24. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  25. 2022Surrogate Gap Minimization Improves Sharpness-Aware Trainingcited by 171
  26. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  27. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  28. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  29. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  30. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  31. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  32. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  33. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  34. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  35. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  36. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  37. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 150
  38. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143

50 most cited of 1,623 All 1,623 (JSON)