全局逻辑与局部搜索：用于可验证工业异常检测的双流多模态上下文学习
Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection
AI总结：
针对工业异常检测难题，提出无训练框架GLLS，利用视觉逻辑图谱组织参考和规范，结合全局逻辑流与细粒度动作流，实验表明其优于基线且决策可追溯
摘要：
大型多模态模型在少样本泛化方面表现出色，但工业异常检测仍具挑战。近期基于优化的方法通过微调改善对齐，但早期部署中缺陷样本稀缺。我们提出全局逻辑与局部搜索（GLLS），这是一个用于参考引导的多模态上下文验证的无训练框架。GLLS使用部分感知视觉逻辑图谱在推理上下文中组织正常参考和结构化规范。它将全局与逻辑流（其中SAM 3提取部分可检查的视觉事实）与细粒度与动作流（其中MCTS在固定预算下选择局部证据裁剪）相结合。在MMAD-QA和其他异常检测数据集上的实验表明，与匹配的和通用的基线相比，有持续的提升，同时在整个检查过程中保持最终诊断决策可追溯到明确的视觉证据。
英文摘要：
Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but they often require many defective samples, which are unavailable in early deployment. We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification. GLLS uses a Part-Aware Visual-Logical Atlas to organize normal references and structured specifications in the inference context. It combines a Global & Logic Stream, where SAM 3 extracts partially checkable visual facts, with a Fine-Grained & Actions Stream, where MCTS selects local evidence crops under a fixed budget. Experiments on MMAD-QA and additional anomaly detection datasets show consistent gains over matched and general-purpose baselines, while keeping the final diagnostic decision traceable to explicit visual evidence throughout the inspection trace.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
