mlsanityData to 14 Oct 2026

Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization

arXiv 2109.15222 ↗First posted 30 Sep 2021cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies (NSA), for training an end-to-end model for anomaly detection and localization using only normal training data. NSA integrates Poisson image editing to seamlessly blend scaled patches of various sizes from separate images. This creates a wide range of synthetic anomalies which are more similar to natural sub-image irregularities than previous data-augmentation strategies for self-supervised anomaly detection. We evaluate the proposed method using natural and medical images. Our experiments with the MVTec AD dataset show that a model trained to localize NSA anomalies generalizes well to detecting real-world a priori unknown types of manufacturing defects. Our method achieves an overall detection AUROC of 97.2 outperforming all previous methods that learn without the use of additional datasets. Code available at https://github.com/hmsch/natural-synthetic-anomalies.

Key facts. Cited by 116 papers in the map (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

27 of 45 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2013Describing Textures in the Wildcited by 2,125
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  8. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  9. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  10. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  11. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  12. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
15 more
  1. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  2. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  3. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  4. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 368
  5. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  6. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  7. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  8. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  9. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  10. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  11. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  12. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
  13. 2020Anomaly detection through latent space restoration using vector-quantized variational autoencoderscited by 45
  14. 2020Detecting Outliers with Foreign Patch Interpolationcited by 44
  15. 2021Detecting Outliers with Poisson Image Interpolationcited by 44

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 22; 2024: 29; 2025: 37; 2026: 20.

116 papers.

Sort:

By area:

  1. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  3. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  4. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  5. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  6. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  7. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  8. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  9. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  10. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  11. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  12. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
38 more
  1. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  2. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  3. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  4. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  5. 2025The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detectioncited by 30
  6. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 27
  7. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 26
  8. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  9. 2024AutoRG-Brain: Grounded Report Generation for Brain MRIcited by 24
  10. 2023Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstructioncited by 23
  11. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detectioncited by 23
  12. 2024Unseen Visual Anomaly Generationcited by 23
  13. 2022A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Imagescited by 21
  14. 2023PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentationcited by 21
  15. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  16. 2022Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detectioncited by 18
  17. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 17
  18. 2025Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detectioncited by 16
  19. 2025NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRIcited by 13
  20. 2023Many tasks make light work: Learning to localise medical anomalies from multiple synthetic taskscited by 12
  21. 2024Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detectioncited by 12
  22. 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detectioncited by 11
  23. 2023REB: Reducing Biases in Representation for Industrial Anomaly Detectioncited by 10
  24. 2024DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learningcited by 10
  25. 2023A Discrepancy Aware Framework for Robust Anomaly Detectioncited by 9
  26. 2023AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rayscited by 8
  27. 2023A Comprehensive Augmentation Framework for Anomaly Detectioncited by 8
  28. 2024AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnosticscited by 8
  29. 2024Few-shot Defect Image Generation based on Consistency Modelingcited by 8
  30. 2024FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Datacited by 8
  31. 2025PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomaliescited by 8
  32. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  33. 2023Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videoscited by 7
  34. 2023No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detectioncited by 7
  35. 2024ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detectioncited by 7
  36. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  37. 2024A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptationcited by 6
  38. 2025Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detectioncited by 6

50 most cited of 116 All 116 (JSON)