mlsanityData to 7 Oct 2026

Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learning

arXiv 2403.15463 ↗First posted 19 Mar 2024cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Anomaly Detection is a relevant problem in numerous real-world applications, especially when dealing with images. However, little attention has been paid to the issue of changes over time in the input data distribution, which may cause a significant decrease in performance. In this study, we investigate the problem of Pixel-Level Anomaly Detection in the Continual Learning setting, where new data arrives over time and the goal is to perform well on new and old data. We implement several state-of-the-art techniques to solve the Anomaly Detection problem in the classic setting and adapt them to work in the Continual Learning setting. To validate the approaches, we use a real-world dataset of images with pixel-based anomalies to provide a reliable benchmark and serve as a foundation for further advancements in the field. We provide a comprehensive analysis, discussing which Anomaly Detection methods and which families of approaches seem more suitable for the Continual Learning setting.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

36 of 51 references.

References · 36

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2016Learning without Forgettingcited by 2,465
  4. 2016Progressive Neural Networkscited by 1,332
  5. 2017Continual Learning with Deep Generative Replaycited by 1,152
  6. 2018Experience Replay for Continual Learningcited by 1,074
  7. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  9. 2019Three scenarios for continual learningcited by 610
  10. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  12. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
24 more
  1. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  2. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  3. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  4. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  5. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
  6. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  7. 2019Latent Replay for Real-Time Continual Learningcited by 97
  8. 2020Rethinking Experience Replay: a Bag of Tricks for Continual Learningcited by 94
  9. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  10. 2020Imbalanced Continual Learning with Partitioning Reservoir Samplingcited by 71
  11. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  12. 2020SpaceNet: Make Free Space For Continual Learningcited by 53
  13. 2017Lifelong Generative Modelingcited by 51
  14. 2018Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgettingcited by 46
  15. 2019Efficient Continual Learning in Neural Networks with Embedding Regularizationcited by 20
  16. 2021Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturingcited by 19
  17. 2022Practical Recommendations for Replay-based Continual Learning Methodscited by 16
  18. 2022Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewardscited by 10
  19. 2022Continual Learning Approaches for Anomaly Detectioncited by 9
  20. 2022A Benchmark and Empirical Analysis for Replay Strategies in Continual Learningcited by 8
  21. 2020ARCADe: A Rapid Continual Anomaly Detectorcited by 7
  22. 2021Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Datacited by 7
  23. 2022Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentationcited by 6
  24. 2020Improving unsupervised anomaly localization by applying multi-scale memories to autoencoderscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 4.

13 papers.

Sort:

  1. 2024PaSTe: Improving the Efficiency of Visual Anomaly Detection at the Edgecited by 16
  2. 2024Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmarkcited by 6
  3. 2025Memory Efficient Continual Learning for Edge-Based Visual Anomaly Detectioncited by 4
  4. 2025Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detectioncited by 4
  5. 2025Towards Continual Visual Anomaly Detection in the Medical Domaincited by 3
  6. 2025From Vision to Sound: Advancing Audio Anomaly Detection with Vision-Based Algorithmscited by 1
  7. 2025MECAD: A multi-expert architecture for continual anomaly detectioncited by 1
  8. 2026Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutionscited by 1
  9. 2025MoViAD: A Modular Library for Visual Anomaly Detectioncited by 0
  10. 2025On-Device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturingcited by 0
  11. 2026AdapTS: Lightweight Teacher-Student Approach for Multi-Class and Continual Visual Anomaly Detectioncited by 0
  12. 2026Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditionscited by 0
1 more
  1. 2026Training-Free Human-in-the-Loop Anomaly Detection via Memory Bank Correctioncited by 0