Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning

TL;DR

This paper introduces RTFM, a novel weakly-supervised video anomaly detection method that enhances positive instance recognition by learning robust feature magnitudes and capturing temporal dependencies, outperforming state-of-the-art methods.

Contribution

The paper proposes RTFM, a theoretically grounded approach that improves anomaly detection by focusing on feature magnitude learning and temporal dependency modeling.

Findings

RTFM outperforms existing methods on four benchmark datasets.

It significantly improves detection of subtle anomalies.

The approach enhances sample efficiency in anomaly detection.

Abstract

Anomaly detection with weakly supervised video-level labels is typically formulated as a multiple instance learning (MIL) problem, in which we aim to identify snippets containing abnormal events, with each video represented as a bag of video snippets. Although current methods show effective detection performance, their recognition of the positive instances, i.e., rare abnormal snippets in the abnormal videos, is largely biased by the dominant negative instances, especially when the abnormal events are subtle anomalies that exhibit only small differences compared with normal events. This issue is exacerbated in many methods that ignore important video temporal dependencies. To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos. RTFM also adapts dilated convolutions and self-attention mechanisms to capture long- and short-range temporal dependencies to learn the feature magnitude more faithfully. Extensive experiments show that the RTFM-enabled MIL model (i) outperforms several state-of-the-art methods by a large margin on four benchmark data sets (ShanghaiTech, UCF-Crime, XD-Violence and UCSD-Peds) and (ii) achieves significantly improved subtle anomaly discriminability and sample efficiency. Code is available at https://github.com/tianyu0207/RTFM.