Boyang Wan, Yuming Fang, Xue Xia, Jiajie Mei
Anomaly detection in surveillance videos is a challenging task due to the diversity of anomalous video content and duration. In this paper, we consider video anomaly detection as a regression problem with respect to anomaly scores of video clips under weak supervision. Hence, we propose an anomaly detection framework, called Anomaly Regression Net (AR-Net), which only requires video-level labels in training stage. Further, to learn discriminative features for anomaly detection, we design a dynamic multiple-instance learning loss and a center loss for the proposed AR-Net. The former is used to enlarge the inter-class distance between anomalous and normal instances, while the latter is proposed to reduce the intra-class distance of normal instances. Comprehensive experiments are performed on a challenging benchmark: ShanghaiTech. Our method yields a new state-of-the-art result for video anomaly detection on ShanghaiTech dataset
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Video Understanding | ShanghaiTech Weakly Supervised | AUC-ROC | 91.24 | AR-Net |
| Video | ShanghaiTech Weakly Supervised | AUC-ROC | 91.24 | AR-Net |
| Anomaly Detection | ShanghaiTech Weakly Supervised | AUC-ROC | 91.24 | AR-Net |
| Anomaly Detection | UBnormal | AUC-ROC | 62.3 | AR-Net |
| Anomaly Detection | ShanghaiTech Weakly Supervised | AUC-ROC | 91.24 | AR-Net |
| Anomaly Detection | ShanghaiTech Weakly Supervised | FAR-Normal | 0.1 | AR-Net |
| 3D Anomaly Detection | UBnormal | AUC-ROC | 62.3 | AR-Net |
| 3D Anomaly Detection | ShanghaiTech Weakly Supervised | AUC-ROC | 91.24 | AR-Net |
| 3D Anomaly Detection | ShanghaiTech Weakly Supervised | FAR-Normal | 0.1 | AR-Net |
| Video Anomaly Detection | UBnormal | AUC-ROC | 62.3 | AR-Net |
| Video Anomaly Detection | ShanghaiTech Weakly Supervised | AUC-ROC | 91.24 | AR-Net |
| Video Anomaly Detection | ShanghaiTech Weakly Supervised | FAR-Normal | 0.1 | AR-Net |