马氏距离 PatchCore：协方差感知与流式兼容的工业异常检测
Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detection
AI总结：
提出马氏距离 PatchCore，通过协方差估计和流式处理改进 PatchCore，在保持性能的同时降低峰值内存并提升工业检测精度。
摘要：
工业视觉异常检测通常是一类问题：正常图像丰富，而缺陷罕见、异质且常在系统设计时不可用。PatchCore 风格的检索适合此场景，因为它通过正常补丁特征的内存库对测试图像评分，但标准欧几里得几何忽略了特征相关性，且其离线构建在子采样前需实例化整个补丁池。我们引入马氏距离 PatchCore，一种协方差感知、流式兼容的 PatchCore 扩展。其人工智能贡献在于一种检索检测器，它在降维特征空间中估计正则化协方差模型并对嵌入进行白化，使得变换后的欧几里得最近邻搜索实现马氏距离检索。一个有界内存、可重复迭代的训练流程通过增量降维、在线协方差估计和流式聚合，无需一次性存储所有正常补丁即可构建内存库。工程应用是自动化工业检测，其中视觉异常检测必须在实际内存限制下保持准确。我们在一个公开的 15 类工业异常检测基准和三个工业数据集（涵盖吹灌封条带安瓿弯月面检测、琥珀色玻璃安瓿底部检测和冻干饼西林瓶检测）上评估该方法。马氏距离 PatchCore 在公开基准上保留了大部分离线 PatchCore 的图像级性能，同时将峰值内存从 5.41 GB 降至 2.78 GB，并将选定的工业平均图像接收者操作特征曲线下面积从 0.981 提升至 0.986。
英文摘要：
Industrial visual anomaly detection is usually one-class: normal images are abundant, while defects are rare, heterogeneous, and often unavailable during system design. PatchCore-style retrieval suits this setting because it scores test images from a memory bank of normal patch features, but the standard Euclidean geometry ignores feature correlations and its offline construction materialises the full patch pool before subsampling. We introduce Mahalanobis PatchCore, a covariance-aware, streaming-compatible extension of PatchCore. Its artificial intelligence contribution is a retrieval detector that estimates a regularised covariance model in reduced feature space and whitens embeddings, so Euclidean nearest-neighbour search after transformation implements Mahalanobis retrieval. A bounded-memory, re-iterable training pipeline builds the memory bank without storing all normal patches at once, using incremental dimensionality reduction, online covariance estimation, and streaming aggregation. The engineering application is automated industrial inspection, where visual anomaly detection must remain accurate under practical memory limits. We evaluate the method on a public 15-category industrial anomaly-detection benchmark and three industrial datasets covering blow-fill-seal strip-ampoule meniscus inspection, amber-glass-ampoule bottom inspection, and lyophilised-cake vial inspection. Mahalanobis PatchCore preserves most offline PatchCore image-level performance on the public benchmark while reducing peak memory from 5.41 to 2.78 GB, and improves the selected industrial mean image area under the receiver operating characteristic curve from 0.981 to 0.986.
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。
