MSN-net: Multi-Scale Normality Network for Video Anomaly Detection
Yang Liu, Di Li, W. J. Zhu, Dingkang Yang, Jing Liu, Liang Song
Abstract
Existing unsupervised video anomaly detection methods often suffer from performance degradation due to the overgeneralization of deep models. In this paper, we propose a simple yet effective Multi-Scale Normality network (MSN-net) that uses hierarchical memories to learn multi-level prototypical spatial-temporal patterns of normal events. Specifically, the hierarchical memory module interacts with the encoder through the reading and writing operations during the training phase, preserving multi-scale normality in three separate memory pools. Then, the decoder decodes the features rewritten by the memorized normality to predict future frames so that its ability to predict anomalies is diminished. Experimental results show that MSN-net performs comparably to the state-of-the-art methods, and extension analysis demonstrates the effectiveness of multi-scale normality learning.