Temporal Convolutional Network with Complementary Inner Bag Loss for Weakly Supervised Anomaly Detection

Jiangong Zhang, Laiyun Qing, Jun Miao

Abstract: Weakly supervised anomaly detection (WSAD) is a challenging task with only normal and anomaly video label supervision but required to localize intervals where anomalies take place. We employ multiple instance learning (MIL) for weakly supervised anomaly detection and define a novel inner bag loss (IBL) for MIL to constrain the function space of weakly supervised problem, which consider the lowest anomaly instance score and highest score in each bag. More specifically, the gap between the lowest score and highest score in a positive bag should be large, and that of a negative bag should be small. In order to model the temporal structure of video, we encode preceding adjacent instance by temporal convolutional network (TCN) explicitly. Experimental results show that temporal convolutional network with complementary inner bag loss outperforms the state-of-the-art on the Crime dataset.