AI RESEARCH
AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
arXiv CS.CV
•
ArXi:2605.30140v1 Announce Type: new Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, they require substantial