Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance

TL;DR

This paper introduces a novel weakly supervised video anomaly detection method that leverages cross-batch clustering guidance to improve feature discriminability and address data imbalance, resulting in more accurate anomaly detection.

Contribution

The method employs a batch clustering loss and cross-batch strategy to enhance feature discrimination and mitigate data imbalance in weakly supervised video anomaly detection.

Findings

Improved anomaly detection accuracy on public datasets.

Effective reduction of data imbalance effects.

Enhanced feature discriminability through clustering loss.

Abstract

Weakly supervised video anomaly detection (WSVAD) is a challenging task since only video-level labels are available for training. In previous studies, the discriminative power of the learned features is not strong enough, and the data imbalance resulting from the mini-batch training strategy is ignored. To address these two issues, we propose a novel WSVAD method based on cross-batch clustering guidance. To enhance the discriminative power of features, we propose a batch clustering based loss to encourage a clustering branch to generate distinct normal and abnormal clusters based on a batch of data. Meanwhile, we design a cross-batch learning strategy by introducing clustering results from previous mini-batches to reduce the impact of data imbalance. In addition, we propose to generate more accurate segment-level anomaly scores based on batch clustering guidance further improving the performance of WSVAD. Extensive experiments on two public datasets demonstrate the effectiveness of our approach.