发表机构
Aalto University; Harbin Engineering University（阿尔托大学; 哈尔滨工程大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种基于正常集校准融合冻结表征线索的无训练异常检测方法，可同时处理逻辑与结构异常，在MVTec-LOCO上表现优于同类无训练检测器，且泛化性良好。
AI 中文摘要
工业异常检测需处理两类不同缺陷：结构异常表现为局部纹理损坏，逻辑异常则违反对象数量、组成或排列的全局规则。现有检测器通常偏向其中一类而牺牲另一类：无训练方法可有效利用冻结表征，但缺乏明确的对象数量概念；而需推理数量的方法通常依赖特定类别的组件建模。本文证明，可在不增加额外训练或部件级监督的情况下，将计数能力引入无训练异常检测。核心思路是采用正常集校准，利用正常图像的统计信息对齐异构异常线索，使其能在统一的无训练框架内直接融合。基于该校准，本文提出的检测器结合互补的冻结线索，可同时处理逻辑与结构异常。在MVTec-LOCO数据集上，本文方法在逻辑异常和结构异常上的图像级AUROC分别为89.0和95.9，平均达92.5，是对比的无训练检测器中表现最佳的；其仍与需网络训练或部件标注的方法具有竞争力，且结构变体在MVTec-AD上的图像级AUROC达99.1，与PatchCore相当，表明所提校准可推广至逻辑异常检测之外的场景。
英文摘要
Industrial anomaly detection must handle two distinct defect families: structural anomalies, which manifest as local texture corruptions, and logical anomalies, which violate global rules on object count, composition, or arrangement. Existing detectors typically favor one family at the expense of the other. In particular, training-free methods effectively exploit frozen representations but lack an explicit notion of object count, while methods that reason about counts usually rely on category-specific component modeling. We show that counting ability can be introduced into training-free anomaly detection without additional training or part-level supervision. Our key idea is a normal-set calibration that aligns heterogeneous anomaly cues using statistics from normal images, enabling their direct fusion within a unified training-free framework. Built upon this calibration, our detector combines complementary frozen cues to address both logical and structural anomalies. On MVTec-LOCO, our method achieves image-level AUROCs of 89.0 and 95.9 on logical and structural anomalies, respectively, yielding a 92.5 average---the best among training-free detectors in our comparison. It remains competitive with methods requiring network training or part annotations, while its structural variant matches PatchCore on MVTec-AD (99.1 image-AUROC), suggesting that the proposed calibration generalizes beyond logical anomaly detection.
CommentsAccepted by PRCV 2026
