AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection 事件

AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection arXiv:2605.30140v1 Announce Type: new Abstract: 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 training on large auxiliary datasets to adapt VLMs to anomaly detection, and their inference largely relies on visual-text emb