Unsupervised, Online and On-the-Fly Anomaly Detection for Non-Stationary Image Distributions

Declan GD McIntosh, Alexandra Branzan Albu

ECCV 2024

doi:10.1007/978-3-031-73030-6_24 /eccv/2024/mcintosh2024eccv-unsupervised/

Abstract

We propose Online-InReaCh, the first fully unsupervised online method for detecting and localizing anomalies on-the-fly in image sequences while following non-stationary distributions. Previous anomaly detection methods are limited to supervised one-class classification or are unsupervised but still pre-compute their nominal model. Online-InReaCh can operate online by dynamically maintaining a nominal model of commonly occurring patches that associate well across image realizations of the underlying nominal distribution while removing stale previously nominal patches. Online-InReaCh, while competitive in previous offline benchmarks, also achieves 0.936 and 0.961 image- and pixel-wise AUROC when tested online on MVTecAD, where 23.8% of all randomly sampled images contain anomalies. Online-InReaCh’s performance did not correlate with anomaly proportion even to 33.5%. We also show that Online-InReaCh can integrate new nominal structures and distinguish anomalies after a single frame, even in the worst-case distribution shift from one training class to a new previously unseen testing class. Code: https://github.com/DeclanMcIntosh/Online_InReaCh

PDF ECCV Semantic Scholar

Cite

Text

McIntosh and Albu. "Unsupervised, Online and On-the-Fly Anomaly Detection for Non-Stationary Image Distributions." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73030-6_24

Markdown

[McIntosh and Albu. "Unsupervised, Online and On-the-Fly Anomaly Detection for Non-Stationary Image Distributions." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/mcintosh2024eccv-unsupervised/) doi:10.1007/978-3-031-73030-6_24

BibTeX

@inproceedings{mcintosh2024eccv-unsupervised,
  title     = {{Unsupervised, Online and On-the-Fly Anomaly Detection for Non-Stationary Image Distributions}},
  author    = {McIntosh, Declan GD and Albu, Alexandra Branzan},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-73030-6_24},
  url       = {https://mlanthology.org/eccv/2024/mcintosh2024eccv-unsupervised/}
}