mlsanityData to 7 Oct 2026

Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection

arXiv 1904.02639 ↗First posted 4 Apr 2019cs.CVcited by 560

Not on the map. Why?

Cited by 23 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep autoencoder has been extensively used for anomaly detection. Training on the normal data, the autoencoder is expected to produce higher reconstruction error for the abnormal inputs than the normal ones, which is adopted as a criterion for identifying anomalies. However, this assumption does not always hold in practice. It has been observed that sometimes the autoencoder "generalizes" so well that it can also reconstruct anomalies well, leading to the miss detection of anomalies. To mitigate this drawback for autoencoder based anomaly detector, we propose to augment the autoencoder with a memory module and develop an improved autoencoder called memory-augmented autoencoder, i.e. MemAE. Given an input, MemAE firstly obtains the encoding from the encoder and then uses it as a query to retrieve the most relevant memory items for reconstruction. At the training stage, the memory contents are updated and are encouraged to represent the prototypical elements of the normal data. At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data. The reconstruction will thus tend to be close to a normal sample. Thus the reconstructed errors on anomalies will be strengthened for anomaly detection. MemAE is free of assumptions on the data type and thus general to be applied to different tasks. Experiments on various datasets prove the excellent generalization and high effectiveness of the proposed MemAE.

Key facts. Cited by 560 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 91; 2022: 104; 2023: 106; 2024: 95; 2025: 93; 2026: 71.

560 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  3. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  4. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  5. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  6. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  7. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  8. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 223
  9. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  10. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  11. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  12. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 137
38 more
  1. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  2. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  3. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  4. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  5. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  6. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  7. 2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
  8. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  9. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  10. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  11. 2022Denoising diffusion models for out-of-distribution detectioncited by 102
  12. 2022CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Drivingcited by 100
  13. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  14. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 91
  15. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  16. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 88
  17. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 87
  18. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  19. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  20. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  21. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  22. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  23. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  24. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  25. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  26. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  27. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 66
  28. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 63
  29. 2021Video Prediction Recalling Long-term Motion Context via Memory Alignment Learningcited by 62
  30. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  31. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 59
  32. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  33. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  34. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 56
  35. 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
  36. 2024Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learningcited by 53
  37. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  38. 2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 48

50 most cited of 560 All 560 (JSON)