mlsanityData to 14 Oct 2026

Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies

arXiv 2405.05886 ↗First posted 9 May 2024cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the trained AE is expected to well reconstruct normal but to poorly reconstruct anomalous data. However, contrary to the expectation, anomalous data is often well reconstructed as well. In order to further separate the reconstruction quality between normal and anomalous data, we propose creating pseudo anomalies from learned adaptive noise by exploiting the aforementioned weakness of AE, i.e., reconstructing anomalies too well. The generated noise is added to the normal data to create pseudo anomalies. Extensive experiments on Ped2, Avenue, ShanghaiTech, CIFAR-10, and KDDCUP datasets demonstrate the effectiveness and generic applicability of our approach in improving the discriminative capability of AEs for anomaly detection.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 33 of its 65 references that are in the map. First posted on arXiv 9 May 2024.

Builds on

33 of 65 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  3. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  4. 2019Face X-ray for More General Face Forgery Detectioncited by 470
  5. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  6. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  7. 2022Detecting Deepfakes with Self-Blended Imagescited by 338
  8. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  9. 2016Learning Temporal Regularity in Video Sequencescited by 254
  10. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  11. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  12. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
21 more
  1. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  2. 2019Adversarial AutoAugmentcited by 111
  3. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  4. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 86
  5. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  6. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  7. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  8. 2020G2D: Generate to Detect Anomalycited by 42
  9. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  10. 2021Learning Not to Reconstruct Anomaliescited by 31
  11. 2018Detecting abnormal events in video using Narrowed Normality Clusterscited by 30
  12. 2020OnlineAugment: Online Data Augmentation with Less Domain Knowledgecited by 28
  13. 2020ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detectioncited by 27
  14. 2021Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detectioncited by 26
  15. 2019Autoencoding Binary Classifiers for Supervised Anomaly Detectioncited by 17
  16. 2017Limiting the Reconstruction Capability of Generative Neural Network using Negative Learningcited by 16
  17. 2021OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detectioncited by 14
  18. 2022Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomaliescited by 14
  19. 2022Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videoscited by 12
  20. 2023PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomaliescited by 8
  21. 2019A Flexible Framework for Anomaly Detection via Dimensionality Reductioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Autoencoders for Anomaly Detection are Unreliablecited by 9
  2. 2025TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detectioncited by 1
  3. 2025Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledgecited by 0
  4. 2026When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detectioncited by 0