发表机构
Sun Yat-sen University; University of Macau（中山大学; 澳门大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RoMod利用稀疏混合专家模型的路由统计作为内部异常线索，提出仅需5%弱标注视频的高效视频异常检测框架，通过路由调制融合和时间网络实现最先进性能。
AI 中文摘要
多模态大语言模型的中间层特征在视频异常检测（VAD）中展现出强大潜力，但其判别能力的来源仍不明确。我们利用稀疏混合专家（MoE）模型研究这一问题，其显式的专家结构和稀疏激活使得内部计算更易于检查。在完全冻结的主干网络且无需额外训练的情况下，我们发现与异常相关的证据集中在少量专家中。这些专家跨层重复出现，自发地专精于不同类型的异常，并共同形成一个动态路由子网络。我们进一步表明，受这些专家影响最强的输出通道也正是包含最多异常相关信息的隐藏维度。因此，路由统计信息可以作为内部异常线索，补充语义线索。基于这些发现，我们提出了RoMod，一种仅使用5%弱标注视频训练的高效VAD框架。RoMod包含路由调制融合模块RoMF和路由感知时间网络RoTN。RoMF利用路由信号自适应地重新校准隐藏语义通道，其设计还防止路由分支绕过语义特征并自行做出预测。RoTN捕捉异常从发生到持续再到终止的时间演化过程。在三个基准上的实验表明，RoMod实现了最先进的性能，同时运行速度显著快于规模相当的非稀疏主干网络。
英文摘要
Intermediate-layer features from multimodal large language models have shown strong potential for video anomaly detection (VAD), yet the origin of their discriminative power remains unclear. We study this question using sparse mixture-of-experts (MoE) models, whose explicit expert structure and sparse activation make their internal computation easier to inspect. With a fully frozen backbone and no additional training, we find that anomaly-related evidence is concentrated in a small set of experts. These experts recur across layers, spontaneously specialize in different anomaly types, and together form a dynamic routing subnetwork. We further show that the output channels most strongly influenced by these experts are also the hidden dimensions that contain the most anomaly-relevant information. Routing statistics can therefore serve as an internal anomaly cue that complements semantic features.Based on these findings, we propose RoMod, an efficient VAD framework trained with only \(5\%\) of weakly labeled videos. RoMod includes a Routing-Modulated Fusion module, RoMF, and a Routing-aware Temporal Network, RoTN. RoMF uses routing signals to adaptively recalibrate hidden semantic channels. Its design also prevents the routing branch from bypassing semantic features and making predictions on its own. RoTN captures the temporal evolution of anomalies from onset to persistence and termination. Experiments on three benchmarks show that RoMod achieves state-of-the-art performance while running substantially faster than dense backbones of comparable size.
