Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detection

ArXi:2605.27748v1 Announce Type: cross 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.