CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection

TL;DR

This paper introduces CLAWS, a weakly supervised anomaly detection method that leverages clustering, normalcy suppression, and batch training to improve detection accuracy in videos with noisy labels.

Contribution

The paper proposes a novel weakly supervised approach combining clustering, normalcy suppression, and batch training to enhance anomaly detection in videos.

Findings

Achieved 83.03% frame-level AUC on UCF Crime dataset.

Achieved 89.67% frame-level AUC on ShanghaiTech dataset.

Outperforms existing state-of-the-art algorithms.

Abstract

Learning to detect real-world anomalous events through video-level labels is a challenging task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we propose a weakly supervised anomaly detection method which has manifold contributions including1) a random batch based training procedure to reduce inter-batch correlation, 2) a normalcy suppression mechanism to minimize anomaly scores of the normal regions of a video by taking into account the overall information available in one training batch, and 3) a clustering distance based loss to contribute towards mitigating the label noise and to produce better anomaly representations by encouraging our model to generate distinct normal and anomalous clusters. The proposed method obtains83.03% and 89.67% frame-level AUC performance on the UCF Crime and ShanghaiTech datasets respectively, demonstrating its superiority over the existing state-of-the-art algorithms.