arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.01633cs.CV
收藏

MIST:多实例自训练视频异常检测框架

MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

Sun Yat-Sen University(中山大学);Peng Cheng Laboratory(鹏城实验室);Pazhou Lab(琶洲实验室)

Jia-Chang Feng, Fa-Ting Hong, Wei-Shi Zheng

摘要:

弱监督视频异常检测(WS-VAD)是一种基于判别式表示的视频异常检测方法。大多数现有的作品是有限的,在不足的视频表示。在这项工作中,我们开发了一个多实例自训练框架(MIST),以有效地完善特定于任务的歧视性表示,只有视频级的注释。特别是,MIST由1)多实例伪标签生成器组成,它采用稀疏连续采样策略来产生更可靠的剪辑级伪标签,以及2)自我引导的注意力提升特征编码器,旨在自动关注帧中的异常区域,同时提取特定于任务的表示。此外,我们采用自训练计划,以优化这两个组件,并最终获得一个特定于任务的特征编码器。在两个公共数据集上的大量实验证明了我们方法的有效性,我们的方法的性能优于或优于现有的监督和弱监督方法,特别是在上海科技大学获得了94.83%的帧级AUC。

英文摘要:

Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a multiple instance self-training framework (MIST)to efficiently refine task-specific discriminative representations with only video-level annotations. In particular, MIST is composed of 1) a multiple instance pseudo label generator, which adapts a sparse continuous sampling strategy to produce more reliable clip-level pseudo labels, and 2) a self-guided attention boosted feature encoder that aims to automatically focus on anomalous regions in frames while extracting task-specific representations. Moreover, we adopt a self-training scheme to optimize both components and finally obtain a task-specific feature encoder. Extensive experiments on two public datasets demonstrate the efficacy of our method, and our method performs comparably to or even better than existing supervised and weakly supervised methods, specifically obtaining a frame-level AUC 94.83% on ShanghaiTech.

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。

↑