BROWSE
Detail
Journal Article
Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos
Cited 14 time in 
Share 
Share
- Authors
- Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, Seung-Ik Lee
- Issue Date
- 2024-10
- Citation
- IEEE Transactions on Neural Networks and Learning Systems, v.35, no.10, pp.14085-14098
- ISSN
- 2162-237X
- Publisher
- IEEE Computational Intelligence Society
- Language
- English
- Type
- Journal Article
- Abstract
- Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data. We propose a weakly supervised anomaly detection system that has multiple contributions including a random batch selection mechanism to reduce interbatch correlation and a normalcy suppression block (NSB) which learns to minimize anomaly scores over normal regions of a video by utilizing the overall information available in a training batch. In addition, a clustering loss block (CLB) is proposed to mitigate the label noise and to improve the representation learning for the anomalous and normal regions. This block encourages the backbone network to produce two distinct feature clusters representing normal and anomalous events. An extensive analysis of the proposed approach is provided using three popular anomaly detection datasets including UCF-Crime, ShanghaiTech, and UCSD Ped2. The experiments demonstrate the superior anomaly detection capability of our approach.
- KSP Keywords
- Backbone Network, Detection Systems(IDS), Label noise, Real-world, Representation learning, Selection mechanism, Surveillance video, anomaly detection system, detection capability, information available, learning system