Hard Nominal Example-aware Template Mutual Matching for Industrial Anomaly Detection
share
Anomaly detectors are widely used in industrial production to detect and localize unknown defects in query images. These detectors are trained on nominal images and have shown success in distinguishing anomalies from most normal samples. However, hard-nominal examples are scattered and far apart from most normalities, they are often mistaken for anomalies by existing anomaly detectors. To address this problem, we propose a simple yet efficient method: Hard Nominal Example-aware Template Mutual Matching (HETMM). Specifically, HETMM aims to construct a robust prototype-based decision boundary, which can precisely distinguish between hard-nominal examples and anomalies, yielding fewer false-positive and missed-detection rates. Moreover, HETMM mutually explores the anomalies in two directions between queries and the template set, and thus it is capable to capture the logical anomalies. This is a significant advantage over most anomaly detectors that frequently fail to detect logical anomalies. Additionally, to meet the speed-accuracy demands, we further propose Pixel-level Template Selection (PTS) to streamline the original template set. PTS selects cluster centres and hard-nominal examples to form a tiny set, maintaining the original decision boundaries. Comprehensive experiments on five real-world datasets demonstrate that our methods yield outperformance than existing advances under the real-time inference speed. Furthermore, HETMM can be hot-updated by inserting novel samples, which may promptly address some incremental learning issues.
READ FULL TEXT
