Anomaly detectors are widely used in industrial manufacturing to detect and localize unknown defects in query images. These detectors are trained on anomaly-free samples and have successfully distinguished anomalies from most normal samples. However, hard-normal examples are scattered and far apart from most normal samples, and thus they are often mistaken for anomalies by existing methods. To address this issue, we propose Hard-normal Example-aware Template Mutual Matching (HETMM), an efficient framework to build a robust prototype-based decision boundary. Specifically, HETMM employs the proposed Affine-invariant Template Mutual Matching (ATMM) to mitigate the affection brought by the affine transformations and easy-normal examples. By mutually matching the pixel-level prototypes within the patch-level search spaces between query and template set, ATMM can accurately distinguish between hard-normal examples and anomalies, achieving low false-positive and missed-detection rates. In addition, we also propose PTS to compress the original template set for speed-up. PTS selects cluster centres and hard-normal examples to preserve the original decision boundary, allowing this tiny set to achieve comparable performance to the original one. Extensive experiments demonstrate that HETMM outperforms state-of-the-art methods, while using a 60-sheet tiny set can achieve competitive performance and real-time inference speed (around 26.1 FPS) on a Quadro 8000 RTX GPU. HETMM is training-free and can be hot-updated by directly inserting novel samples into the template set, which can promptly address some incremental learning issues in industrial manufacturing.

异常检测器广泛用于工业制造中，用于检测和定位查询图像中的未知缺陷。这些检测器在无异常样本上进行训练，并成功地将异常与大多数正常样本区分开来。然而，硬正规样本是分散的，与大多数正规样本相距甚远，因此它们经常被现有方法误认为是异常。为了解决这个问题，我们提出了 Hard-normal Example-aware Template Mutual Matching （HETMM），这是一个构建鲁棒的基于原型的决策边界的有效框架。具体来说，HETMM 采用所提出的 Affine-invariant Template Mutual Matching （ATMM） 来减轻仿射变换和易法态示例带来的影响。通过在查询和模板集之间的补丁级搜索空间内相互匹配像素级原型，ATMM 可以准确区分硬正常示例和异常，从而实现较低的误报率和漏检率。此外，我们还建议使用 PTS 对原始模板集进行压缩，以加快速度。PTS 选择聚类中心和硬法线样本来保留原始决策边界，使这个小集合能够实现与原始集合相当的性能。大量实验表明，HETMM 的性能优于最先进的方法，而使用 60 页的微型集可以在 Quadro 8000 RTX GPU 上实现有竞争力的性能和实时推理速度（约 26.1 FPS）。 HETMM 无需训练，可以通过直接在模板集中插入新样本进行热更新，可以及时解决工业制造中的一些增量学习问题。