CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection
This work addresses logical anomaly detection for industrial inspection by providing an unsupervised approach that eliminates manual annotations, though it is incremental as it builds on existing segmentation and anomaly detection methods.
The paper tackles the problem of logical anomaly detection by developing an unsupervised component segmentation technique that autonomously generates training labels using foundation models, achieving a detection AUROC of 95.3% on the MVTec LOCO AD dataset and surpassing previous state-of-the-art methods.
To improve logical anomaly detection, some previous works have integrated segmentation techniques with conventional anomaly detection methods. Although these methods are effective, they frequently lead to unsatisfactory segmentation results and require manual annotations. To address these drawbacks, we develop an unsupervised component segmentation technique that leverages foundation models to autonomously generate training labels for a lightweight segmentation network without human labeling. Integrating this new segmentation technique with our proposed Patch Histogram module and the Local-Global Student-Teacher (LGST) module, we achieve a detection AUROC of 95.3% in the MVTec LOCO AD dataset, which surpasses previous SOTA methods. Furthermore, our proposed method provides lower latency and higher throughput than most existing approaches.