Although various weakly supervised anomaly detection methods have been proposed in recent years, generalization of anomaly detection is still not well-explored. Existing weakly supervised methods usually use normal and abnormal events to pose anomaly detection as a regression problem. However, defining concepts that encompass all possible normal and abnormal event patterns is nearly unrealistic, so the anomaly detection model is likely to face both open normal and abnormal events in practical applications. We find some weakly supervised anomaly detection methods suffer from performance degradation when faced with open events due to their poor generalization. To tackle this issue, we propose a two-branch weakly supervised approach, which can improve the anomaly detection performance of open events without affecting the performance of the seen events. Specifically, considering that the pattern of open events is different from that of seen events, we design a Test Data Analyzer (TDA) that determines whether the test video features belong to seen or open data and argue for separate treatment for them. For the seen data, a classifier trained by multiple instance learning is used to predict anomaly scores. For the open data, we design an anomaly detection model via meta-learning named Meta-Learning Anomaly Detection (MLAD), which can directly determine whether open data is abnormal without updating model parameters. In detail, MLAD synthesizes pseudo-seen data and pseudo-open data so that the model can learn to detect anomalies in open data by transferring the knowledge of seen data. Experimental results validate the effectiveness of our proposed method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events


    Contributors:
    Zhang, Chen (author) / Li, Guorong (author) / Xu, Qianqian (author) / Zhang, Xinfeng (author) / Su, Li (author) / Huang, Qingming (author)

    Published in:

    Publication date :

    2022-11-01


    Size :

    2579543 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Weakly supervised object localization and segmentation in videos

    Rochan, M. / Rahman, S. / Bruce, N. D. et al. | British Library Online Contents | 2016


    Weakly-Supervised Crack Detection

    Inoue, Yuki / Nagayoshi, Hiroto | IEEE | 2023


    Towards Anomaly Detection in Dashcam Videos

    Haresh, Sanjay / Kumar, Sateesh / Zia, M. Zeeshan et al. | IEEE | 2020


    A Three-Stage Anomaly Detection Framework for Traffic Videos

    Junzhou Chen / Jiancheng Wang / Jiajun Pu et al. | DOAJ | 2022

    Free access

    Automatic action annotation in weakly labeled videos

    Sultani, Waqas / Shah, Mubarak | British Library Online Contents | 2017