mlsanityData to 7 Oct 2026

Learning Memory-guided Normality for Anomaly Detection

arXiv 2003.13228 ↗First posted 30 Mar 2020cs.CVcited by 278

Not on the map. Why?

Abstract (arXiv)

We address the problem of anomaly detection, that is, detecting anomalous events in a video sequence. Anomaly detection methods based on convolutional neural networks (CNNs) typically leverage proxy tasks, such as reconstructing input video frames, to learn models describing normality without seeing anomalous samples at training time, and quantify the extent of abnormalities using the reconstruction error at test time. The main drawbacks of these approaches are that they do not consider the diversity of normal patterns explicitly, and the powerful representation capacity of CNNs allows to reconstruct abnormal video frames. To address this problem, we present an unsupervised learning approach to anomaly detection that considers the diversity of normal patterns explicitly, while lessening the representation capacity of CNNs. To this end, we propose to use a memory module with a new update scheme where items in the memory record prototypical patterns of normal data. We also present novel feature compactness and separateness losses to train the memory, boosting the discriminative power of both memory items and deeply learned features from normal data. Experimental results on standard benchmarks demonstrate the effectiveness and efficiency of our approach, which outperforms the state of the art.

Key facts. Cited by 278 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 53; 2022: 56; 2023: 56; 2024: 51; 2025: 39; 2026: 23.

278 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. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  4. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  5. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  6. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  7. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  8. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  9. 2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
  10. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  11. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  12. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 91
38 more
  1. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  2. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 88
  3. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  4. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 87
  5. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 85
  6. 2021OadTR: Online Action Detection with Transformerscited by 83
  7. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  8. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  9. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  10. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  11. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  12. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  13. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  14. 2021Video Prediction Recalling Long-term Motion Context via Memory Alignment Learningcited by 62
  15. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  16. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 59
  17. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  18. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 55
  19. 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
  20. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  21. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
  22. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  23. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  24. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 47
  25. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  26. 2023Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detectioncited by 43
  27. 2023A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipationcited by 42
  28. 2023Diversity-Measurable Anomaly Detectioncited by 41
  29. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  30. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  31. 2021Video-based Person Re-identification with Spatial and Temporal Memory Networkscited by 35
  32. 2023Anomaly Detection under Distribution Shiftcited by 35
  33. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  34. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  35. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  36. 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
  37. 2021Learning Not to Reconstruct Anomaliescited by 31
  38. 2022ADTR: Anomaly Detection Transformer with Feature Reconstructioncited by 31

50 most cited of 278 All 278 (JSON)