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.
翻译:微弱监督的视频异常现象检测旨在识别仅使用视频级标签的视频中的异常事件。 最近,两阶段的自我培训方法通过自我生成假标签和这些标签的自我完善异常分数取得了显著改进。 由于伪标签发挥着关键作用,我们提议了一个强化框架,利用完整性和不确定性特性进行有效的自我培训。 具体地说, 我们首先设计一个多头分类模块( 每位头部作为分类师), 以尽可能扩大预测的假标签在头部之间的分布差异。 这鼓励生成的假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假标签精细化战略, 不仅改进初始假标签,而且改进了第二阶段想要的分类者获得的更新标签。 广泛的实验结果表明,拟议的方法优于UCF-C-Crime、TAD和XD-vivil基准数据集方面的最先进的方法。