Consistency-Based Self-Supervised Learning for Temporal Anomaly Localization
Abstract
This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization of anomalous activities within the video stream: this is a very challenging scenario, as training examples come only with video-level annotations (and not frame-level). Several recent works have proposed various regularization terms to address it i.e. by enforcing sparsity and smoothness constraints over the weakly-learned frame-level anomaly scores. In this work, we get inspired by recent advances within the field of self-supervised learning and ask the model to yield the same scores for different augmentations of the same video sequence. We show that enforcing such an alignment improves the performance of the model on XD-Violence.
Cite
Text
Panariello et al. "Consistency-Based Self-Supervised Learning for Temporal Anomaly Localization." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25072-9_22Markdown
[Panariello et al. "Consistency-Based Self-Supervised Learning for Temporal Anomaly Localization." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/panariello2022eccvw-consistencybased/) doi:10.1007/978-3-031-25072-9_22BibTeX
@inproceedings{panariello2022eccvw-consistencybased,
title = {{Consistency-Based Self-Supervised Learning for Temporal Anomaly Localization}},
author = {Panariello, Aniello and Porrello, Angelo and Calderara, Simone and Cucchiara, Rita},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {338-349},
doi = {10.1007/978-3-031-25072-9_22},
url = {https://mlanthology.org/eccvw/2022/panariello2022eccvw-consistencybased/}
}