3 papers
cs.CV2025
AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation
Qingqing Fang, Wenxi Lv, Qinliang Su
Visual anomaly detection has been widely used in industrial inspection and medical diagnosis. Existing methods typically demand substantial training samples, limiting their utility…
cs.CV2024
Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning
Qingqing Fang, Qinliang Su, Wenxi Lv +2
Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the ano…
cs.CV2024
AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model
Zhenyu Yan, Qingqing Fang, Wenxi Lv +1
Anomaly detection is a critical task in industrial manufacturing, aiming to identify defective parts of products. Most industrial anomaly detection methods assume the availability…