arXiv 2602.098502026-05-08cs.CV

面向可解释性工业异常检测的基于知识引导的潜在推理

Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning

School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区计算机科学与技术学院）；School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）

Peng Chen, Chao Huang, Yunkang Cao, Chengliang Liu, Wei Wang, Wenqiang Wang, Mingbo Yang, Li Shen, Wenqi Ren, Xiaochun Cao

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Reason-IAD框架，通过引入领域特定文本描述和熵驱动的潜在推理机制，提升工业异常检测的准确性和可解释性，实验表明其在多个任务中均优于现有方法。

摘要：

工业异常检测需要对细粒度缺陷模式进行精确推理。然而，现有多模态大语言模型（MLLMs）在通用领域数据上预训练，难以捕捉类别特定的异常，限制了检测准确性和可解释性。为此，我们提出Reason-IAD，一种基于知识引导的动态潜在推理框架，用于可解释性工业异常检测。Reason-IAD包含两个核心组件。首先，检索增强的知识模块将类别特定的文本描述纳入模型输入，实现对领域特定缺陷的上下文感知推理。其次，熵驱动的潜在推理机制在紧凑的潜在空间中进行迭代探索，利用基于熵的奖励鼓励自信稳定的预测。此外，动态视觉注入策略选择性地将最信息丰富的图像块纳入潜在序列，引导推理过程向异常检测关键区域。大量实验结果表明，Reason-IAD在多个任务中均优于现有方法。代码将在https://github.com/chenpeng052/Reason-IAD上公开。

英文摘要：

Industrial anomaly detection demands precise reasoning over fine-grained defect patterns. However, existing multimodal large language models (MLLMs), pretrained on general-domain data, often struggle to capture category-specific anomalies, thereby limiting both detection accuracy and interpretability. To address these limitations, we propose Reason-IAD, a knowledge-guided dynamic latent reasoning framework for explainable industrial anomaly detection. Reason-IAD comprises two core components. First, a retrieval-augmented knowledge module incorporates category-specific textual descriptions into the model input, enabling context-aware reasoning over domain-specific defects. Second, an entropy-driven latent reasoning mechanism conducts iterative exploration within a compact latent space using optimizable latent think tokens, guided by an entropy-based reward that encourages confident and stable predictions. Furthermore, a dynamic visual injection strategy selectively incorporates the most informative image patches into the latent sequence, directing the reasoning process toward regions critical for anomaly detection. Extensive experimental results demonstrate that Reason-IAD consistently outperforms state-of-the-art methods across multiple tasks. The code will be publicly available at https://github.com/chenpeng052/Reason-IAD.

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。