面向开放词表工业缺陷理解的大规模多模态数据集
Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset
提供了一个百万级图文对齐的工业缺陷数据集，可用于训练和评测视觉语言基础模型在缺陷分类、分割、检索、描述生成上的开放词表能力；其从零训练扩散式视觉语言基础模型、再用不到 5% 任务数据轻量微调即达到专家模型水平的范式，对做领域自适应和少样本迁移的视觉研究者有直接参考价值。
原文依据 we train a diffusion-based vision-language foundation model from scratch, specifically tailored for industrial scenarios
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 IMDD-1M，这是首个大规模工业多模态缺陷数据集，包含 100 万对对齐的图像-文本对，旨在推动面向制造与质量检测的多模态学习。IMDD-1M 涵盖 60 多个材料类别、400 多种缺陷类型的高分辨率真实缺陷，每张图像均配有经专家核验的标注以及细粒度文本描述，详细说明缺陷位置、严重程度与上下文属性。该数据集支持广泛的应用，包括分类、分割、检索、描述生成与生成式建模。基于 IMDD-1M，我们从零训练了一个扩散式视觉语言基础模型，专门针对工业场景定制。该模型可作为可泛化的基础模型，通过轻量微调高效适配到专门领域。它仅需专用专家模型所需任务特定数据的不到 5%，即可达到与之相当的性能，凸显了数据高效的基础模型适配在工业检测与生成方面的潜力，为可扩展、领域自适应且知识驱动的制造智能铺平了道路。
英文原文摘要 1229 字符
We present IMDD-1M, the first large-scale Industrial Multimodal Defect Dataset comprising 1,000,000 aligned image-text pairs, designed to advance multimodal learning for manufacturing and quality inspection. IMDD-1M contains high-resolution real-world defects spanning over 60 material categories and more than 400 defect types, each accompanied by expert-verified annotations and fine-grained textual descriptions detailing defect location, severity, and contextual attributes. This dataset enables a wide spectrum of applications, including classification, segmentation, retrieval, captioning, and generative modeling. Building upon IMDD-1M, we train a diffusion-based vision-language foundation model from scratch, specifically tailored for industrial scenarios. The model serves as a generalizable foundation that can be efficiently adapted to specialized domains through lightweight fine-tuning. With less than 5% of the task-specific data required by dedicated expert models, it achieves comparable performance, highlighting the potential of data-efficient foundation model adaptation for industrial inspection and generation, paving the way for scalable, domain-adaptive, and knowledge-grounded manufacturing intelligence.