弱监督视频异常检测中帧级AUC的审计：粒度、分辨率与场景偏差
Auditing Frame-Level AUC in Weakly Supervised Video Anomaly Detection: Granularity, Resolution, and Scene Bias
浏览论文内容
中文总结 AI 辅助
该研究针对弱监督视频异常检测的帧级AUC审计，发现其存在定位预测不可靠、分辨率不足、受场景偏差影响等问题，并公开了粒度感知协议。
中文摘要 AI 辅助
帧级ROC曲线下面积（AUC）是弱监督视频异常检测（WSVAD）的主流评估指标，其标准形式用于衡量异常帧是否优于测试集中任意位置的正常帧，该比较被称为池化AUC，因它聚合了测试视频间的帧对而不考虑来源，池化AUC同时兼顾事件定位和视频来源间的差异。我们在UCF-Crime数据集上对近期不同骨干网络系列的SOTA模型审计该协议，固定每个模型的帧得分，在三种配对粒度下读取：全局、每个异常类别内、每个视频内，再对模型内部表示计算的零样本得分重复相同的三粒度读取，用配对视频自举法评估排序可靠性，得到三个发现：第一，池化AUC无法可靠预测视频内异常定位，池化得分相近的模型在更严格粒度下表现出巨大的定位差异和排序反转；第二，在基准测试集划分规模下，池化AUC缺乏支持领域报告的SOTA差值的分辨率，在每个骨干网络系列内，该差值下无比较结果，而视频内AUC在相同预测下可得到多个结果，学习到的表示进一步揭示视频内异常结构与检测器定位是解耦的；第三，仅在正常视频素材上，所有被检查的模型都会按分辨率、色彩编码等录制属性区分视频，表明场景敏感性是该设置下的共性而非特定于某一架构。我们公开发布了一种可基于现有预测和UCF-Crime的场景因子注释计算的粒度感知协议。
英文摘要
Frame-level area under the ROC curve (AUC) is the dominant evaluation metric for weakly supervised video anomaly detection (WSVAD). Its standard form measures whether an anomalous frame outranks a normal frame drawn from anywhere in the test set. We refer to this comparison as pooled AUC, since it aggregates frame pairs across test videos regardless of source. Pooled AUC therefore credits both event localization and differences between video sources. We audit this protocol on UCF-Crime across recent state-of-the-art models spanning different backbone families. Holding each model's frame scores fixed, we read them under three pairing granularities: global, per anomaly category, and within each video, then repeat the same three-granularity readout on zero-shot scores computed from the models' internal representations. We assess ranking reliability with a paired video bootstrap. Three findings follow. First, pooled AUC does not reliably predict within-video anomaly localization: models with similar pooled scores exhibit large localization differences and rank reversals under stricter granularities. Second, at the benchmark's test-split size, pooled AUC lacks the resolution to support state-of-the-art margins reported in the field. Within each backbone family, it resolves no comparison at those margins, while within-video AUC resolves several over identical predictions. Learned representations further reveal that within-video anomaly structure and detector localization are decoupled. Third, on normal footage alone, every model we examine separates videos by recording properties, such as resolution and color encoding, indicating that scene sensitivity is shared across the setting rather than specific to any architecture. We publicly release a granularity-aware protocol computable from existing predictions and scene-factor annotations for UCF-Crime.
发表机构
- Eindhoven University of Technology（埃因霍温理工大学）
机构由 AI 辅助整理，请以论文原文为准。
