AgentIAD: 通过自适应记忆增强的代理工业异常检测
AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation
AI总结：
本文提出AgentIAD框架，通过统一的动作空间实现迭代工业检测，利用视觉记忆和检索记忆进行多轮感知-行动推理，提升异常检测准确性和可解释性。
摘要：
工业异常检测（IAD）因缺陷的细微和高度局部化而具有挑战性，单次通过视觉-语言模型（VLMs）常难以捕捉。此外，现有方法缺乏在推理过程中主动获取互补证据的机制。我们提出AgentIAD，一种代理视觉-语言框架，通过统一的动作空间实现迭代工业检查。代理在检查过程中动态访问两种形式的记忆：通过Perceptive Zoomer（PZ）进行视觉记忆以实现细粒度局部分析，以及通过Web Searcher（WS）和Comparative Retriever（CR）进行外部知识获取和跨实例验证。此设计使模型能够通过多轮感知-行动推理逐步收集证据。为了在稀疏监督下有效学习此类策略，AgentIAD采用两阶段训练策略：首先通过工具感知监督微调初始化结构化推理和记忆访问行为，随后通过代理强化学习优化长周期决策策略。大量实验表明，在相同主干网络下，AgentIAD在MMAD基准上比先前最先进的方法提高了5.92%的分类准确率，同时提供了更可靠和可解释的异常分析。
英文摘要：
Industrial anomaly detection (IAD) is challenging due to the subtle and highly localized nature of many defects, which single-pass vision--language models (VLMs) often fail to capture. Moreover, existing approaches lack mechanisms to actively acquire complementary evidence during inference. We propose AgentIAD, an agentic vision--language framework that enables iterative industrial inspection through a unified action space. The agent dynamically accesses two forms of memory during inspection: visual memory via the Perceptive Zoomer (PZ) for fine-grained local analysis, and retrieved memory via the Web Searcher (WS) and Comparative Retriever (CR) for external knowledge acquisition and cross-instance verification. This design allows the model to progressively gather evidence through multi-round perception--action reasoning. To effectively learn such policies under sparse supervision, AgentIAD adopts a two-stage training strategy: tool-aware supervised fine-tuning first initializes structured reasoning and memory-access behaviors, followed by agentic reinforcement learning to refine long-horizon decision policies. Extensive experiments show that, under the same backbone, AgentIAD improves classification accuracy by 5.92% over the previous state-of-the-art method on the MMAD benchmark while providing more reliable and interpretable anomaly analysis.
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。
