Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization

ArXi:2309.13904v3 Announce Type: replace Unsupervised anomaly localization aims to identify anomalous regions that deviate from normal sample patterns. Most recent methods perform feature matching or reconstruction for the target sample with pre-trained deep neural networks. However, they still struggle to address challenging anomalies because the deep embeddings d in the memory bank can be less powerful and informative. Specifically, prior methods often overly rely on the finite resources d in the memory bank, which leads to low robustness to unseen targets.