ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications
This addresses efficient anomaly detection in video surveillance, offering a lightweight solution with competitive performance.
The paper tackles the problem of label ambiguity in weakly-supervised video anomaly detection by proposing ProDisc-VAD, which achieves strong AUCs of 97.98% on ShanghaiTech and 87.12% on UCF-Crime with only 0.4M parameters, over 800x fewer than recent ViT-based methods.
Weakly-supervised video anomaly detection (WS-VAD) using Multiple Instance Learning (MIL) suffers from label ambiguity, hindering discriminative feature learning. We propose ProDisc-VAD, an efficient framework tackling this via two synergistic components. The Prototype Interaction Layer (PIL) provides controlled normality modeling using a small set of learnable prototypes, establishing a robust baseline without being overwhelmed by dominant normal data. The Pseudo-Instance Discriminative Enhancement (PIDE) loss boosts separability by applying targeted contrastive learning exclusively to the most reliable extreme-scoring instances (highest/lowest scores). ProDisc-VAD achieves strong AUCs (97.98% ShanghaiTech, 87.12% UCF-Crime) using only 0.4M parameters, over 800x fewer than recent ViT-based methods like VadCLIP. Code is available at https://github.com/modadundun/ProDisc-VAD.