GCR：面向任务无关持续异常检测的几何一致性路由
GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection
AI总结：
GCR通过几何一致性路由提升持续异常检测的稳定性，减少遗忘并保持检测性能。
摘要：
基于特征的异常检测在工业检测中被广泛应用，因为大预训练视觉编码器具有强大的表示能力。虽然大多数现有方法专注于改进类别内异常评分，但实际部署越来越多地需要在持续类别扩展下进行任务无关操作，其中测试时类别身份是未知的。在这种情况下，整体性能通常由专家选择主导，即在任何特定头部评分之前，将输入路由到合适的正常性模型。然而，比较独立构建的头部特定异常评分的路由规则在实践中不可靠，因为不同类别的分数分布可能在规模和尾部行为上差异显著。我们提出了GCR，一种轻量级的专家混合框架，通过几何一致性路由来稳定任务无关的持续异常检测。GCR通过在共享冻结的补丁嵌入空间中最小化累积最近原型距离到类别特定原型库，直接对每个测试图像进行路由，并使用标准原型基于评分规则仅在路由的专家内部计算异常图。通过将跨头部决策与头部内异常评分分离，GCR在不需要端到端表示学习的情况下避免了跨头部评分可比性问题。在MVTec AD和VisA上的实验表明，几何一致性路由显著提高了路由稳定性并缓解了持续性能崩溃，实现了接近零遗忘的同时保持竞争性的检测和定位性能。这些结果表明，许多以前归因于表示遗忘的失败可以由跨头部路由中的决策规则不稳定来解释。代码可在https://github.com/jw-chae/GCR上获得。
英文摘要：
Feature-based anomaly detection is widely adopted in industrial inspection due to the strong representational power of large pre-trained vision encoders. While most existing methods focus on improving within-category anomaly scoring, practical deployments increasingly require task-agnostic operation under continual category expansion, where the category identity is unknown at test time. In this setting, overall performance is often dominated by expert selection, namely routing an input to an appropriate normality model before any head-specific scoring is applied. However, routing rules that compare head-specific anomaly scores across independently constructed heads are unreliable in practice, as score distributions can differ substantially across categories in scale and tail behavior. We propose GCR, a lightweight mixture-of-experts framework for stabilizing task-agnostic continual anomaly detection through geometry-consistent routing. GCR routes each test image directly in a shared frozen patch-embedding space by minimizing an accumulated nearest-prototype distance to category-specific prototype banks, and then computes anomaly maps only within the routed expert using a standard prototype-based scoring rule. By separating cross-head decision making from within-head anomaly scoring, GCR avoids cross-head score comparability issues without requiring end-to-end representation learning. Experiments on MVTec AD and VisA show that geometry-consistent routing substantially improves routing stability and mitigates continual performance collapse, achieving near-zero forgetting while maintaining competitive detection and localization performance. These results indicate that many failures previously attributed to representation forgetting can instead be explained by decision-rule instability in cross-head routing. Code is available at https://github.com/jw-chae/GCR
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。
