Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detection

TL;DR

This paper introduces a weakly supervised anomaly detection method that uses clustering to reduce label noise, achieving state-of-the-art results on video anomaly datasets.

Contribution

It proposes a novel clustering-based approach to mitigate label noise in weakly supervised video anomaly detection.

Findings

Achieves 78.27% frame-level AUC on UCF-crime

Achieves 84.16% frame-level AUC on ShanghaiTech

Outperforms existing state-of-the-art methods

Abstract

Learning to detect real-world anomalous events using video-level annotations is a difficult task mainly because of the noise present in labels. An anomalous labelled video may actually contain anomaly only in a short duration while the rest of the video can be normal. In the current work, we formulate a weakly supervised anomaly detection method that is trained using only video-level labels. To this end, we propose to utilize binary clustering which helps in mitigating the noise present in the labels of anomalous videos. Our formulation encourages both the main network and the clustering to complement each other in achieving the goal of weakly supervised training. The proposed method yields 78.27% and 84.16% frame-level AUC on UCF-crime and ShanghaiTech datasets respectively, demonstrating its superiority over existing state-of-the-art algorithms.