Test Time Training for Industrial Anomaly Segmentation

arXiv:2404.03743v1 Announce Type: new
Abstract: Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical applications require producing a binary segmentation to identify anomalies. Due to the absence of labeled anomalies in many real scenarios, standard practices binarize these maps based on some statistics derived from a validation set containing only nominal samples, resulting in poor segmentation performance. This paper addresses this problem by proposing a test …

abstract anomaly anomaly detection applications arxiv binary control cs.cv detection excel identify industrial maps pixel practical practices quality segmentation standard test training type