-
[pdf]
[supp]
[bibtex]@InProceedings{Doshi_2022_WACV, author = {Doshi, Keval and Yilmaz, Yasin}, title = {Rethinking Video Anomaly Detection - A Continual Learning Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {3961-3970} }
Rethinking Video Anomaly Detection - A Continual Learning Approach
Abstract
While video anomaly detection has been an active area of research for several years, recent progress is limited to improving the state-of-the-art results on small datasets using an inadequate evaluation criterion. In this work, we take a new comprehensive look at the video anomaly detection problem from a more realistic perspective. Specifically, we consider practical challenges such as continual learning and few-shot learning, which humans can easily do but remains to be a significant challenge for machines. A novel algorithm designed for such practical challenges is also proposed. For performance evaluation in this new framework, we introduce a new dataset which is significantly more comprehensive than the existing benchmark datasets, and a new performance metric which takes into account the fundamental temporal aspect of video anomaly detection. The experimental results show that the existing state-of-the-art methods are not suitable for the considered practical challenges, and the proposed algorithm outperforms them with a large margin in continual learning and few-shot learning tasks.
Related Material