Abstract: Autoencoder (AE) is extensively utilized in hyperspectral anomaly detection (HAD) tasks owing to its robust feature extraction and image reconstruction capabilities. However, AE lacks ...

Abstract: As a core problem in unsupervised learning, anomaly detection focuses on identifying abnormal patterns in datasets, thereby providing support for uncovering potential problems and extracting ...

[JMS 2026] A Comprehensive Survey for Real-World Industrial Surface Defect Detection: Challenges, Approaches, and Prospects (Journal of Manufacturing Systems) ...

We propose EAGLE, a tuning-free framework for anomaly detection. The framework comprises two core components: (1) a PatchCore-based expert model that performs preliminary anomaly detection and ...