mlsanityData to 7 Oct 2026

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

arXiv 2303.10704 ↗First posted 19 Mar 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Due to the rarity of anomalous events, video anomaly detection is typically approached as one-class classification (OCC) problem. Typically in OCC, an autoencoder (AE) is trained to reconstruct the normal only training data with the expectation that, in test time, it can poorly reconstruct the anomalous data. However, previous studies have shown that, even trained with only normal data, AEs can often reconstruct anomalous data as well, resulting in a decreased performance. To mitigate this problem, we propose to limit the anomaly reconstruction capability of AEs by incorporating pseudo anomalies during the training of an AE. Extensive experiments using five types of pseudo anomalies show the robustness of our training mechanism towards any kind of pseudo anomaly. Moreover, we demonstrate the effectiveness of our proposed pseudo anomaly based training approach against several existing state-ofthe-art (SOTA) methods on three benchmark video anomaly datasets, outperforming all the other reconstruction-based approaches in two datasets and showing the second best performance in the other dataset.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 41 of its 92 references that are in the map. First posted on arXiv 19 Mar 2023.

Builds on

41 of 92 references.

References · 41

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  5. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  6. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  7. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  8. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  9. 2016Learning Temporal Regularity in Video Sequencescited by 254
  10. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  11. 2020Deep Learning for Anomaly Detection: A Reviewcited by 159
  12. 2018Latent Space Autoregression for Novelty Detectioncited by 149
29 more
  1. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  2. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  3. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
  4. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 89
  5. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 85
  6. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  7. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  8. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  9. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  10. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  11. 2020Continual Learning for Anomaly Detection in Surveillance Videoscited by 49
  12. 2020G2D: Generate to Detect Anomalycited by 42
  13. 2020Any-Shot Sequential Anomaly Detection in Surveillance Videoscited by 34
  14. 2020Learning a distance function with a Siamese network to localize anomalies in videoscited by 31
  15. 2021Learning Not to Reconstruct Anomaliescited by 31
  16. 2018Detecting abnormal events in video using Narrowed Normality Clusterscited by 30
  17. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  18. 2020ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detectioncited by 27
  19. 2021Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detectioncited by 26
  20. 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
  21. 2022Perturbation Learning Based Anomaly Detectioncited by 24
  22. 2018STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detectioncited by 17
  23. 2019Autoencoding Binary Classifiers for Supervised Anomaly Detectioncited by 17
  24. 2017Limiting the Reconstruction Capability of Generative Neural Network using Negative Learningcited by 16
  25. 2019Local Deep-Feature Alignment for Unsupervised Dimension Reductioncited by 12
  26. 2019Anomaly Detection in Particulate Matter Sensor using Hypothesis Pruning Generative Adversarial Networkcited by 9
  27. 2020AEGCN: An Autoencoder-Constrained Graph Convolutional Networkcited by 5
  28. 2018Learning to Make Predictions on Graphs with Autoencoderscited by 4
  29. 2022ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variablescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 1; 2026: 2.

8 papers.

  1. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  2. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  3. 2024Dynamic Distinction Learning: Adaptive Pseudo Anomalies for Video Anomaly Detectioncited by 6
  4. 2024Exploiting Autoencoder's Weakness to Generate Pseudo Anomaliescited by 4
  5. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  6. 2024Appearance Blur-driven AutoEncoder and Motion-guided Memory Module for Video Anomaly Detectioncited by 3
  7. 2026Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detectioncited by 0
  8. 2026Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluatedcited by 0