Decoupled Sensitivity-Consistency Learning for Weakly Supervised Video Anomaly Detection

TL;DR

The paper introduces DeSC, a decoupled learning framework for weakly supervised video anomaly detection that balances sensitivity to transient events with long-term consistency, achieving state-of-the-art results.

Contribution

DeSC decouples sensitivity and consistency streams with distinct optimization strategies, improving detection accuracy in weakly supervised video anomaly detection.

Findings

Achieves 89.37% AUC on UCF-Crime

Attains 87.18% AP on XD-Violence

Outperforms previous methods with +1.29% and +2.22% improvements

Abstract

Recent weakly supervised video anomaly detection methods have achieved significant advances by employing unified frameworks for joint optimization. However, this paradigm is limited by a fundamental sensitivity-stability trade-off, as the conflicting objectives for detecting transient and sustained anomalies lead to either fragmented predictions or over-smoothed responses. To address this limitation, we propose DeSC, a novel Decoupled Sensitivity-Consistency framework that trains two specialized streams using distinct optimization strategies. The temporal sensitivity stream adopts an aggressive optimization strategy to capture high-frequency abrupt changes, whereas the semantic consistency stream applies robust constraints to maintain long-term coherence and reduce noise. Their complementary strengths are fused through a collaborative inference mechanism that reduces individual biases and produces balanced predictions. Extensive experiments demonstrate that DeSC establishes new state-of-the-art performance by achieving 89.37% AUC on UCF-Crime (+1.29%) and 87.18% AP on XD-Violence (+2.22%). Code is available at https://github.com/imzht/DeSC.