适配视觉-语言模型用于工业目标检测中的人类可读可解释人工智能
Adapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection
浏览论文内容
中文总结 AI 辅助
针对工业目标检测中现有XAI方法对非专家用户不友好的问题，提出基于微调视觉-语言模型的解释界面，在专有及公开数据集上较GPT 4o-mini显著提升解释清晰度与上下文感知，增强了AI解释的可访问性。
中文摘要 AI 辅助
可解释人工智能（XAI）解决方案对于建立对AI技术的信任及其在真实制造生产线中的集成至关重要。然而，大多数现有方法都是针对技术专家量身定制的，限制了不同用户群体（如生产线上使用AI进行质量控制的蓝领工人）对其的可访问性。在这项工作中，我们介绍了一种基于微调视觉-语言模型的工业制造目标检测XAI界面，旨在为非专家用户生成直观的解释。我们对现有视觉-语言模型进行了基准测试，并证明开箱即用的模型在向非专家用户提供清晰、与上下文相关的解释方面往往表现不足。为解决这一问题，我们微调了一个视觉-语言模型并将其集成到我们的界面中，从而能够为非专家用户提供情境化、可理解的解释。我们展示了在专有和公开机器人数据集上，相较于GPT 4o-mini，在解释清晰度、指令遵循、图像接地性和上下文感知方面的改进。该方法推进了AI解释的可访问性和可用性，使其在制造领域更加直观和适用。
英文摘要
Explainable Artificial Intelligence (XAI) solutions are essential for building trust in AI technologies and their integration in real manufacturing lines. However, most existing methods are tailored to technical experts, limiting their accessibility to diverse user groups such as blue-collar workers in manufacturing lines who use AI for quality control. In this work, we introduce an XAI interface for object detection in industrial manufacturing based on a fine-tuned vision-language model, designed to generate intuitive explanations for non-expert users. We benchmark existing vision-language models and demonstrate that out-of-the-box models often fall short in delivering clear, context-relevant explanations for non-expert users. To address this, we fine-tune a vision-language model and integrate it into our interface, enabling contextualized, accessible explanations for non-expert users. We demonstrate improvements in explanation clarity, instruction adherence, image groundedness, and contextual awareness over GPT 4o-mini on proprietary and public robotics dataset. This approach advances the accessibility and usability of AI explanations, making them more intuitive and applicable in manufacturing domain.
发表机构
- Mercedes-Benz AG（梅赛德斯-奔驰股份公司）
- University of Stuttgart（斯图加特大学）
机构由 AI 辅助整理，请以论文原文为准。
