Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection

TL;DR

This paper introduces a Global-Local Correspondence Framework using a semantic bottleneck and visual Transformer to detect both structural and logical anomalies in visual data, outperforming existing methods.

Contribution

The paper proposes a novel two-branch framework with a semantic bottleneck for detecting high-level logical anomalies alongside structural ones.

Findings

Outperforms existing methods on industrial and medical datasets.

Effective detection of logical anomalies involving high-level constraints.

Validated on multiple benchmarks including Mvtec AD and Retinal-OCT.

Abstract

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.