mlsanityData to 14 Oct 2026

Learning Not to Reconstruct Anomalies

arXiv 2110.09742 ↗First posted 19 Oct 2021cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

Video anomaly detection is often seen as one-class classification (OCC) problem due to the limited availability of anomaly examples. Typically, to tackle this problem, an autoencoder (AE) is trained to reconstruct the input with training set consisting only of normal data. At test time, the AE is then expected to well reconstruct the normal data while poorly reconstructing the anomalous data. However, several studies have shown that, even with only normal data training, AEs can often start reconstructing anomalies as well which depletes the anomaly detection performance. To mitigate this problem, we propose a novel methodology to train AEs with the objective of reconstructing only normal data, regardless of the input (i.e., normal or abnormal). Since no real anomalies are available in the OCC settings, the training is assisted by pseudo anomalies that are generated by manipulating normal data to simulate the out-of-normal-data distribution. We additionally propose two ways to generate pseudo anomalies: patch and skip frame based. Extensive experiments on three challenging video anomaly datasets demonstrate the effectiveness of our method in improving conventional AEs, achieving state-of-the-art performance.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 31 of its 61 references that are in the map. First posted on arXiv 19 Oct 2021.

Builds on

31 of 61 references.

References · 31

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  3. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  4. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  5. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  6. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  7. 2016Learning Temporal Regularity in Video Sequencescited by 254
  8. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  9. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  10. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  11. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  12. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
19 more
  1. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  2. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 90
  3. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  4. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  5. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  6. 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
  7. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  8. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  9. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  10. 2020Continual Learning for Anomaly Detection in Surveillance Videoscited by 49
  11. 2020G2D: Generate to Detect Anomalycited by 42
  12. 2020Any-Shot Sequential Anomaly Detection in Surveillance Videoscited by 34
  13. 2020Learning a distance function with a Siamese network to localize anomalies in videoscited by 31
  14. 2018Detecting abnormal events in video using Narrowed Normality Clusterscited by 30
  15. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  16. 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
  17. 2018STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detectioncited by 17
  18. 2019Autoencoding Binary Classifiers for Supervised Anomaly Detectioncited by 17
  19. 2017Limiting the Reconstruction Capability of Generative Neural Network using Negative Learningcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 5; 2024: 7; 2025: 7; 2026: 3.

31 papers.

Sort:

By area:

  1. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  2. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  3. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  4. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  5. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  6. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  7. 2022Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detectioncited by 27
  8. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  9. 2022Cross-Domain Video Anomaly Detection without Target Domain Adaptationcited by 20
  10. 2022Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videoscited by 12
  11. 2023Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approachcited by 10
  12. 2025Autoencoders for Anomaly Detection are Unreliablecited by 9
19 more
  1. 2023PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomaliescited by 8
  2. 2024VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detectioncited by 8
  3. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  4. 2025SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Modelcited by 6
  5. 2023Reconstruction Error-based Anomaly Detection with Few Outlying Examplescited by 5
  6. 2024Exploiting Autoencoder's Weakness to Generate Pseudo Anomaliescited by 4
  7. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  8. 2022Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillationcited by 3
  9. 2025Rethinking Metrics and Benchmarks of Video Anomaly Detectioncited by 3
  10. 2024Targeted Augmented Data for Audio Deepfake Detectioncited by 2
  11. 2024Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Datacited by 1
  12. 2025Fast reconstruction-based ROI triggering via anomaly detection in the CYGNO optical TPCcited by 1
  13. 2023Synthetic Pseudo Anomalies for Unsupervised Video Anomaly Detection: A Simple yet Efficient Framework based on Masked Autoencodercited by 0
  14. 2024Exploring the Magnitude-Shape Plot Framework for Anomaly Detection in Crowded Video Scenescited by 0
  15. 2025Video Anomaly Detection with Contours -- A Studycited by 0
  16. 2025GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detectioncited by 0
  17. 2026Semantic-Deviation-Anchored Multi-Branch Fusion for Unsupervised Anomaly Detection and Localization in Unstructured Conveyor-Belt Coal Scenescited by 0
  18. 2026Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluatedcited by 0
  19. 2026When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detectioncited by 0