arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04090cs.CV
收藏

利用伪标记的完整性和不确定性进行弱监督视频异常检测

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

Institute of Information Engineering, CAS(中国科学院信息工程研究所);University of Chinese Academy of Sciences(中国科学院大学);Australian Institute for Machine Learning, The University of Adelaide(阿德莱德大学澳大利亚机器学习研究所);Institute of Computing Technology, CAS(中国科学院计算技术研究所);Peng Cheng Laboratory(鹏城实验室);University of California, Merced(加州大学默塞德分校)

Chen Zhang, Guorong Li, Yuankai Qi, Shuhui Wang, Laiyun Qing, Qingming Huang, Ming-Hsuan Yang

摘要:

弱监督视频异常检测旨在仅使用视频级标签来识别视频中的异常事件。最近,两阶段的自训练方法已经取得了显着的改进,通过自生成的伪标签和自精炼的异常分数与这些标签。由于伪标签起着至关重要的作用,我们提出了一个增强框架,利用完整性和不确定性属性进行有效的自我训练。具体来说,我们首先设计了一个多头分类模块(每个头作为一个分类器)的多样性损失,以最大限度地提高预测的伪标签的分布差异头。这鼓励生成的伪标签覆盖尽可能多的异常事件。然后,我们设计了一个迭代的不确定性伪标签细化策略,它不仅提高了初始的伪标签,但也更新所需的分类器在第二阶段获得的。大量的实验结果表明,该方法在UCF-Crime,EQUIPMENT和XD-Violence基准数据集上表现良好。

英文摘要:

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑