IADGPT：基于上下文学习的统一 LVLM，用于少样本工业异常检测、定位与推理
IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
AI总结：
提出统一框架 IADGPT，通过三阶段渐进式训练和上下文学习提升少样本工业异常检测、定位与推理能力，并构建了 10 万图像的新数据集。
摘要：
少样本工业异常检测（FS-IAD）在自动化工业质量检测中具有重要应用。近期，一些基于大型视觉语言模型（LVLMs）的 FS-IAD 方法被提出，通过提示学习或微调取得了一些成果。然而，现有的 LVLMs 专注于通用任务，但缺乏与 FS-IAD 相关的基础工业知识和推理能力，使得这些方法远不及专业的人类质量检查员。为了应对这些挑战，我们提出了一个统一框架 IADGPT，旨在以类人的方式执行 FS-IAD，同时处理相关的定位和推理任务，甚至适用于多样化和新颖的工业产品。为此，我们引入了一种受人类启发的三阶段渐进式训练策略。具体而言，前两个阶段逐步引导 IADGPT 获取基础工业知识和差异感知能力。在第三阶段，我们设计了一种基于上下文学习的训练范式，使 IADGPT 能够利用少样本图像作为示例，以提升对新产品的泛化能力。此外，我们设计了一种策略，使 IADGPT 能够分别使用 logits 输出和注意力图输出图像级和像素级异常分数，并结合语言输出来完成异常推理。为了支持我们的训练，我们提供了一个新数据集，包含 100K 张图像，涵盖 400 个多样化的工业产品类别，并附带广泛的属性级文本标注。实验表明，IADGPT 在异常检测方面取得了显著的性能提升，并在异常定位和推理方面展现出竞争力。我们将在最终版中发布我们的数据集。
英文摘要：
Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language Models (LVLMs) have been proposed with some achievements through prompt learning or fine-tuning. However, existing LVLMs focus on general tasks but lack basic industrial knowledge and reasoning capabilities related to FS-IAD, making these methods far from specialized human quality inspectors. To address these challenges, we propose a unified framework, IADGPT, designed to perform FS-IAD in a human-like manner, while also handling associated localization and reasoning tasks, even for diverse and novel industrial products. To this end, we introduce a three-stage progressive training strategy inspired by humans. Specifically, the first two stages gradually guide IADGPT in acquiring fundamental industrial knowledge and discrepancy awareness. In the third stage, we design an in-context learning-based training paradigm, enabling IADGPT to leverage a few-shot image as the exemplars for improved generalization to novel products. In addition, we design a strategy that enables IADGPT to output image-level and pixel-level anomaly scores using the logits output and the attention map, respectively, in conjunction with the language output to accomplish anomaly reasoning. To support our training, we present a new dataset comprising 100K images across 400 diverse industrial product categories with extensive attribute-level textual annotations. Experiments indicate IADGPT achieves considerable performance gains in anomaly detection and demonstrates competitiveness in anomaly localization and reasoning. We will release our dataset in camera-ready.
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。
