Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection
This addresses a gap in visual anomaly detection for applications like industrial inspection and medical diagnosis by improving detection of high-level logical anomalies, though it appears incremental as it builds on existing anomaly detection methods.
The paper tackles the problem of detecting logical anomalies in visual data, which existing methods often miss, by proposing a Global-Local Correspondence Framework (GLCF) that uses a two-branch approach with a semantic bottleneck. Experimental results show it outperforms existing methods, especially in detecting logical anomalies on benchmarks like Mvtec AD and Retinal-OCT.
This paper presents a novel framework, named Global-Local Correspondence Framework (GLCF), for visual anomaly detection with logical constraints. Visual anomaly detection has become an active research area in various real-world applications, such as industrial anomaly detection and medical disease diagnosis. However, most existing methods focus on identifying local structural degeneration anomalies and often fail to detect high-level functional anomalies that involve logical constraints. To address this issue, we propose a two-branch approach that consists of a local branch for detecting structural anomalies and a global branch for detecting logical anomalies. To facilitate local-global feature correspondence, we introduce a novel semantic bottleneck enabled by the visual Transformer. Moreover, we develop feature estimation networks for each branch separately to detect anomalies. Our proposed framework is validated using various benchmarks, including industrial datasets, Mvtec AD, Mvtec Loco AD, and the Retinal-OCT medical dataset. Experimental results show that our method outperforms existing methods, particularly in detecting logical anomalies.