mlsanityData to 7 Oct 2026

A Unifying Review of Deep and Shallow Anomaly Detection

arXiv 2009.11732 ↗First posted 24 Sep 2020cs.LG cs.AI stat.MLcited by 423

Not on the map. Why?

Abstract (arXiv)

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection.

Key facts. Cited by 423 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 58; 2022: 102; 2023: 86; 2024: 69; 2025: 58; 2026: 50.

423 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  3. 2022Transformers in Time Series: A Surveycited by 489
  4. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  5. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  6. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  7. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  8. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  9. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  10. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  11. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  12. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
38 more
  1. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  2. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  3. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  4. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  5. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  6. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  7. 2022Training OOD Detectors in their Natural Habitatscited by 86
  8. 2023On Diffusion Modeling for Anomaly Detectioncited by 71
  9. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  10. 2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
  11. 2021FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learningcited by 67
  12. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  13. 2024Real-Time Anomaly Detection and Reactive Planning with Large Language Modelscited by 67
  14. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  15. 2024Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progresscited by 63
  16. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  17. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  18. 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
  19. 2021Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAycited by 53
  20. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  21. 2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
  22. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  23. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  24. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  25. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  26. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  27. 2022Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxelscited by 42
  28. 2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
  29. 2021Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signalscited by 41
  30. 2022A Survey on Explainable Anomaly Detectioncited by 39
  31. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  32. 2025Failure Prediction at Runtime for Generative Robot Policiescited by 36
  33. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  34. 2021Confidence-based Out-of-Distribution Detection: A Comparative Study and Analysiscited by 34
  35. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  36. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  37. 2021Autoencoders for unsupervised anomaly detection in high energy physicscited by 32
  38. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32

50 most cited of 423 All 423 (JSON)