用分层视觉语言模型实现实时视频异常检测，速度提升150倍且准确率超97%。
Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models
- 离线学习正常行为规则，线上结合轻量过滤与细粒度推理
- 在NVIDIA L40S上达57.68帧/秒，较现有方法快151.79倍
- 通过运动掩码提示和规则偏离检测，提升定位精度与实时性
视频异常检测（VAD）近年来得益于视觉语言模型（VLMs）的发展而快速进步。尽管这些模型具备出色的零样本检测能力，但其巨大的计算开销和不稳定的视觉定位性能阻碍了实时部署。为此，我们提出Cerberus，一种两级级联系统，旨在实现高效且准确的实时VAD。Cerberus离线学习正常行为规则，并在在线推理中结合轻量级过滤与细粒度VLM推理。性能提升源于两项关键创新：运动掩码提示和基于规则的偏离检测。前者引导VLM关注运动相关区域，后者将异常识别为对已学规范的偏离，而非枚举可能异常。在四个数据集上的广泛评估表明，Cerberus在NVIDIA L40S GPU上平均达到57.68 fps，速度提升151.79×，准确率达97.2%，与最先进的VLM-based VAD方法相当，成为实时视频分析的实用解决方案。
原文摘要 · Abstract (English)
Video anomaly detection (VAD) has rapidly advanced by recent development of Vision-Language Models (VLMs). While these models offer superior zero-shot detection capabilities, their immense computational cost and unstable visual grounding performance hinder real-time deployment. To overcome these challenges, we introduce Cerberus, a two-stage cascaded system designed for efficient yet accurate real-time VAD. Cerberus learns normal behavioral rules offline, and combines lightweight filtering with fine-grained VLM reasoning during online inference. The performance gains of Cerberus come from two key innovations: motion mask prompting and rule-based deviation detection. The former directs the VLM's attention to regions relevant to motion, while the latter identifies anomalies as deviations from learned norms rather than enumerating possible anomalies. Extensive evaluations on four datasets show that Cerberus on average achieves 57.68 fps on an NVIDIA L40S GPU, a 151.79$\times$ speedup, and 97.2\% accuracy comparable to the state-of-the-art VLM-based VAD methods, establishing it as a practical solution for real-time video analytics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。