Anomaly Detection Requires Better Representations
Abstract
Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation learning have directly driven improvements in anomaly detection. In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks. We then argue that tackling the next generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.
Cite
Text
Reiss et al. "Anomaly Detection Requires Better Representations." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25069-9_4Markdown
[Reiss et al. "Anomaly Detection Requires Better Representations." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/reiss2022eccvw-anomaly/) doi:10.1007/978-3-031-25069-9_4BibTeX
@inproceedings{reiss2022eccvw-anomaly,
title = {{Anomaly Detection Requires Better Representations}},
author = {Reiss, Tal and Cohen, Niv and Horwitz, Eliahu and Abutbul, Ron and Hoshen, Yedid},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {56-68},
doi = {10.1007/978-3-031-25069-9_4},
url = {https://mlanthology.org/eccvw/2022/reiss2022eccvw-anomaly/}
}