Vision-guided multi-image prompt learning for zero and few-shot pipeline anomaly detection

Efficient few-shot visual anomaly detection and localization via prompt tuning

Cross-Modal Guidance Learning for Zero-Shot Industrial Anomaly Detection

Zero-shot industrial anomaly detection (ZIAD) aims to develop a unified model capable of directly identifying unseen anomaly categories in images without requiring reference samples. Recently, large-scale Vision-Language Models (VLMs) such as CLIP have shown great potential for solving this task. However, existing meth...

GRASP: Enhancing Zero-Shot Multi-Modal Anomaly Detection via Geometric Refinement and Semantic Prompting

A unified zero-shot multimodal anomaly detection framework GRASP is proposed, with substantial improvements of 3.0 points in I-AUROC and 2.7 points in AUPRO compared to the SOTA method.

Multi-level visual-language models feature learning for generalizable anomaly detection

Zero-shot anomaly detection (ZSAD) aims to identify anomalies in target datasets without accessing their samples. Although CLIP and other large-scale vision language models show strong generalization, their potential for multi-level feature extraction in ZSAD remains underexplored. To address this, we propose a Multi...

SAMPromptAD-SWDR: region-level prompt learning with SAM guidance for few-shot defect detection in steel weld DR images

FreqPrompt-AD: Frequency-guided local semantic prompting for zero-shot industrial anomaly detection and segmentation

FreqPrompt-AD achieves the strongest average performance among the compared zero-shot VLM-based detectors in the authors' local full-scale evaluation, improving average image-level and pixel-level AUROC over DLVP-CLIP by 2.15 percentage points.