Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learning (2403.15463v1)

Published 19 Mar 2024 in cs.CV and cs.LG

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Continual learning for anomaly detection with variational autoencoder. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 3837–3841, 2019.
  2. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014.
  3. Mvtec ad — a comprehensive real-world dataset for unsupervised anomaly detection. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9584–9592, 2019.
  4. Reconstruction by inpainting for visual anomaly detection. Pattern Recognition, 112:107706, 2021.
  5. Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows, 2021.
  6. Gido M. van de Ven and Andreas S. Tolias. Three scenarios for continual learning. CoRR, abs/1904.07734, 2019.
  7. A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence, 44(7):3366–3385, 2021.
  8. ANTHONY ROBINS. Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Science, 7(2):123–146, 1995.
  9. Practical recommendations for replay-based continual learning methods.
  10. Continual learning with deep generative replay. Advances in neural information processing systems, 30, 2017.
  11. Experience replay for continual learning. Advances in Neural Information Processing Systems, 32, 2019.
  12. An online continual object detector on vhr remote sensing images with class imbalance. Engineering Applications of Artificial Intelligence, 117:105549, 2023.
  13. Pseudo-rehearsal: Achieving deep reinforcement learning without catastrophic forgetting. Neurocomputing, 428:291–307, 2021.
  14. Relay hindsight experience replay: Self-guided continual reinforcement learning for sequential object manipulation tasks with sparse rewards. Neurocomputing, 557:126620, 2023.
  15. Efficient continual learning in neural networks with embedding regularization. Neurocomputing, 397:139–148, 2020.
  16. Lifelong generative modeling. Neurocomputing, 404:381–400, 2020.
  17. Online continual learning via the meta-learning update with multi-scale knowledge distillation and data augmentation. Engineering Applications of Artificial Intelligence, 113:104966, 2022.
  18. Spacenet: Make free space for continual learning. Neurocomputing, 439:1–11, 2021.
  19. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In Proceedings of the European Conference on Computer Vision (ECCV), pages 67–82, 2018.
  20. Random path selection for continual learning. Advances in Neural Information Processing Systems, 32, 2019.
  21. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521–3526, 2017.
  22. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, 40(12):2935–2947, 2017.
  23. Progressive neural networks. arXiv preprint arXiv:1606.04671, 2016.
  24. Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734, 2017.
  25. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 7765–7773, 2018.
  26. A benchmark and empirical analysis for replay strategies in continual learning, 2022.
  27. Latent replay for real-time continual learning. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 10203–10209. IEEE, 2020.
  28. Rethinking experience replay: a bag of tricks for continual learning. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 2180–2187. IEEE, 2021.
  29. Imbalanced continual learning with partitioning reservoir sampling. In European Conference on Computer Vision, pages 411–428. Springer, 2020.
  30. Learn to detect objects incrementally. In 2018 IEEE Intelligent Vehicles Symposium (IV), pages 403–408. IEEE, 2018.
  31. Bmad: Benchmarks for medical anomaly detection. arXiv preprint arXiv:2306.11876, 2023.
  32. Im-iad: Industrial image anomaly detection benchmark in manufacturing. IEEE Transactions on Cybernetics, 2024.
  33. Regularization-based continual learning for anomaly detection in discrete manufacturing. Procedia CIRP, 104:452–457, 2021.
  34. Continual learning for unsupervised anomaly detection in continuous auditing of financial accounting data. arXiv preprint arXiv:2112.13215, 2021.
  35. Continual learning for anomaly based network intrusion detection. In 2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS), pages 497–505. IEEE, 2022.
  36. Steps towards continual learning in multivariate time-series anomaly detection using variational autoencoders. In Proceedings of the 22nd ACM Internet Measurement Conference, pages 774–775, 2022.
  37. Arcade: A rapid continual anomaly detector. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 10449–10456. IEEE, 2021.
  38. Incremental learning-based algorithm for anomaly detection using computed tomography data. Computation, 11(7):139, 2023.
  39. Towards continual adaptation in industrial anomaly detection. In Proceedings of the 30th ACM International Conference on Multimedia, pages 2871–2880, 2022.
  40. Im-iad: Industrial image anomaly detection benchmark in manufacturing. arXiv preprint arXiv:2301.13359, 2023.
  41. Continual learning approaches for anomaly detection. arXiv preprint arXiv:2212.11192, 2022.
  42. DRAEM - A discriminatively trained reconstruction embedding for surface anomaly detection. arXiv:2108.07610, 2021.
  43. Student-teacher feature pyramid matching for anomaly detection. arXiv:2103.04257, 2021.
  44. Efficientad: Accurate visual anomaly detection at millisecond-level latencies. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 128–138, 2024.
  45. PaDiM: A patch distribution modeling framework for anomaly detection and localization. In Pattern Recognition. ICPR International Workshops and Challenges, pages 475–489. Springer International Publishing, 2021.
  46. Towards total recall in industrial anomaly detection. arXiv:2106.08265, 2022.
  47. Cfa: Coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. IEEE Access, 10:78446–78454, 2022.
  48. Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders. arXiv preprint arXiv:2012.11113, 2020.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now