高效检测自动驾驶等实时系统中的异常行为。
STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications
- 结合(2+1)D卷积与线性注意力，兼顾时空特征提取效率。
- 在UCF-Crime数据集上，基础版AUC达91.34%，快速版参数减少99.7%。
- 适合对延迟和算力敏感的实时异常检测场景，如自动驾驶。
本文提出一种针对时间与计算资源敏感系统的新型异常检测方法——STEAD（Spatio-Temporal Efficient Anomaly Detection），适用于自动驾驶等需实时推理的应用。现有方法多关注空间上下文，缺乏对时序上下文的有效建模与效率优化。为此，我们设计基于(2+1)D卷积与Performer线性注意力的模型，在保持高性能的同时显著降低计算开销。在UCF-Crime基准测试中，基础模型实现91.34%的AUC，优于先前最优；其快速版本参数量仅占原模型的0.3%，仍达到88.87% AUC，且性能超越此前最佳方法。代码与预训练模型已开源。
原文摘要 · Abstract (English)
This paper presents a new method for anomaly detection in automated systems with time and compute sensitive requirements, such as autonomous driving, with unparalleled efficiency. As systems like autonomous driving become increasingly popular, ensuring their safety has become more important than ever. Therefore, this paper focuses on how to quickly and effectively detect various anomalies in the aforementioned systems, with the goal of making them safer and more effective. Many detection systems have been developed with great success under spatial contexts; however, there is still significant room for improvement when it comes to temporal context. While there is substantial work regarding this task, there is minimal work done regarding the efficiency of models and their ability to be applied to scenarios that require real-time inference, i.e., autonomous driving where anomalies need to be detected the moment they are within view. To address this gap, we propose STEAD (Spatio-Temporal Efficient Anomaly Detection), whose backbone is developed using (2+1)D Convolutions and Performer Linear Attention, which ensures computational efficiency without sacrificing performance. When tested on the UCF-Crime benchmark, our base model achieves an AUC of 91.34%, outperforming the previous state-of-the-art, and our fast version achieves an AUC of 88.87%, while having 99.70% less parameters and outperforming the previous state-of-the-art as well. The code and pretrained models are made publicly available at https://github.com/agao8/STEAD
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。