Component-aware anomaly detection framework for adjustable and logical industrial visual inspection

TL;DR

This paper introduces ComAD, a component-aware framework for industrial visual inspection that enables adjustable and logical anomaly detection by segmenting images into components and modeling their relationships, achieving state-of-the-art results.

Contribution

The paper presents a novel framework combining unsupervised segmentation with logical anomaly detection, enhancing adjustability and interpretability in industrial inspection tasks.

Findings

Achieves state-of-the-art performance on logical anomaly detection

Provides a flexible, component-based perspective for industrial inspection

Demonstrates robustness and potential for model customization

Abstract

Industrial visual inspection aims at detecting surface defects in products during the manufacturing process. Although existing anomaly detection models have shown great performance on many public benchmarks, their limited adjustability and ability to detect logical anomalies hinder their broader use in real-world settings. To this end, in this paper, we propose a novel component-aware anomaly detection framework (ComAD) which can simultaneously achieve adjustable and logical anomaly detection for industrial scenarios. Specifically, we propose to segment images into multiple components based on a lightweight and nearly training-free unsupervised semantic segmentation model. Then, we design an interpretable logical anomaly detection model through modeling the metrological features of each component and their relationships. Despite its simplicity, our framework achieves state-of-the-art performance on image-level logical anomaly detection. Meanwhile, segmenting a product image into multiple components provides a novel perspective for industrial visual inspection, demonstrating great potential in model customization, noise resistance, and anomaly classification. The code will be available at https://github.com/liutongkun/ComAD.