Test Time Training for Industrial Anomaly Segmentation
This addresses a practical issue in industrial quality control for scenarios with unlabeled anomalies, though it is incremental as it builds on existing anomaly detection methods.
The paper tackles the problem of poor binary segmentation performance in industrial anomaly detection by proposing a test time training strategy that uses features from anomalous samples to train a classifier, demonstrating effectiveness on MVTec AD and MVTec 3D-AD datasets.
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 time training strategy to improve the segmentation performance. Indeed, at test time, we can extract rich features directly from anomalous samples to train a classifier that can discriminate defects effectively. Our general approach can work downstream to any AD&S method that provides an anomaly score map as output, even in multimodal settings. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD.