Prioritized Local Matching Network for Cross-Category Few-Shot Anomaly Detection

Abstract

In response to the rapid evolution of products in industrial inspection, this article introduces the cross-category few-shot anomaly detection (C-FSAD) task, aimed at efficiently detecting anomalies in new object categories with minimal normal samples. However, the diversity of defects and significant visual distinctions among various objects hinder the identification of anomalous regions. To tackle this, we adopt a pairwise comparison between query and normal samples, establishing an intimate correlation through fine-grained correspondence. Specifically, we propose the prioritized local matching network (PLMNet), emphasizing local analysis of correlation, which includes three primary components: 1) Local perception network refines the initial matches through bidirectional local analysis; 2) step aggregation strategy employs multiple stages of local convolutional pooling to aggregate local insights; and 3) defect-sensitive Weight Learner adaptively enhances channels informative for defect structures, ensuring more discriminative representations of encoded context. Our PLMNet deepens the interpretation of correlations, from geometric cues to semantics, efficiently extracting discrepancies in feature space. Extensive experiments on two standard industrial anomaly detection benchmarks demonstrate our state-of-the-art performance in both detection and localization, with margins of 9.8% and 5.4%, respectively.