mlsanityData to 7 Oct 2026

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

arXiv 2104.04015 ↗First posted 8 Apr 2021cs.CVcited by 529

Not on the map. Why?

Cited by 26 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. We learn representations by classifying normal data from the CutPaste, a simple data augmentation strategy that cuts an image patch and pastes at a random location of a large image. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects. We bring the improvement upon previous arts by 3.1 AUCs when learning representations from scratch. By transfer learning on pretrained representations on ImageNet, we achieve a new state-of-theart 96.6 AUC. Lastly, we extend the framework to learn and extract representations from patches to allow localizing defective areas without annotations during training.

Key facts. Cited by 529 papers in the map (data through 7 Oct 2026). Builds on 43 of its 67 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

43 of 67 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  11. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
31 more
  1. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  2. 2017Random Erasing Data Augmentationcited by 1,235
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  4. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  10. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  13. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  14. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  15. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 231
  16. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  17. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  18. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  19. 2020Classification-Based Anomaly Detection for General Datacited by 210
  20. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  21. 2020Explainable Deep One-Class Classificationcited by 126
  22. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  23. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  24. 2020Density of States Estimation for Out-of-Distribution Detectioncited by 74
  25. 2020Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noisecited by 39
  26. 2019Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicalitycited by 30
  27. 2020Puzzle-AE: Novelty Detection in Images through Solving Puzzlescited by 23
  28. 2020Steering Self-Supervised Feature Learning Beyond Local Pixel Statisticscited by 19
  29. 2016Identifying and Categorizing Anomalies in Retinal Imaging Datacited by 18
  30. 2019Attribute Restoration Framework for Anomaly Detectioncited by 16
  31. 2020Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networkscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 85; 2023: 109; 2024: 121; 2025: 115; 2026: 70.

529 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  3. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  4. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  5. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  6. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  7. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  8. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  9. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  10. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  11. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  12. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
38 more
  1. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  4. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  5. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  6. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  7. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  8. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  9. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  10. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  11. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  12. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  13. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  14. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  15. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  16. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 89
  17. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  18. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  19. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 79
  20. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  21. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  22. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  23. 2022UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detectioncited by 69
  24. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  25. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  26. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  27. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  28. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  29. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 66
  30. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  31. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 62
  32. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  33. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  34. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  35. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  36. 2022SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakescited by 49
  37. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  38. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47

50 most cited of 529 All 529 (JSON)