arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01151cs.CV
收藏

Detect2Interact:利用大语言模型在视觉问答(VQA)中定位物体关键区域

Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs

Northumbria University(诺森比亚大学)

Jialou Wang, Manli Zhu, Yulei Li, Honglei Li, Longzhi Yang, Wai Lok Woo

AI总结:

本文提出Detect2Interact方法,结合SAM空间映射、Vision Studio语义描述与GPT-4常识知识,实现VQA中物体关键区域的细粒度检测,并优于现有基于物体检测的VQA系统。

摘要:

定位在提升视觉问答(VQA)系统的实用性和精确性方面发挥着至关重要的作用。通过实现对物体特定部位的细粒度识别与交互,定位能力显著增强了系统提供上下文相关且空间准确回答的能力,这对于机器人技术和增强现实等动态环境中的应用尤为关键。然而,传统系统在准确映射图像中的物体以生成细致且具备空间感知能力的回答方面面临挑战。在本工作中,我们提出了“Detect2Interact”,通过引入一种面向细粒度物体视觉关键区域检测的先进方法来解决上述挑战。首先,我们使用分割一切模型(SAM)生成图像中物体的详细空间映射。其次,我们利用Vision Studio提取物体的语义描述。第三,我们借助GPT-4的常识知识,弥合物体语义与其空间映射之间的鸿沟。结果表明,Detect2Interact在大量测试用例上实现了物体关键区域检测的一致定性结果,并通过提供更合理、更精细的视觉表示,优于现有的基于物体检测的VQA系统。

英文摘要:

Localization plays a crucial role in enhancing the practicality and precision of VQA systems. By enabling fine-grained identification and interaction with specific parts of an object, it significantly improves the system's ability to provide contextually relevant and spatially accurate responses, crucial for applications in dynamic environments like robotics and augmented reality. However, traditional systems face challenges in accurately mapping objects within images to generate nuanced and spatially aware responses. In this work, we introduce "Detect2Interact", which addresses these challenges by introducing an advanced approach for fine-grained object visual key field detection. First, we use the segment anything model (SAM) to generate detailed spatial maps of objects in images. Next, we use Vision Studio to extract semantic object descriptions. Third, we employ GPT-4's common sense knowledge, bridging the gap between an object's semantics and its spatial map. As a result, Detect2Interact achieves consistent qualitative results on object key field detection across extensive test cases and outperforms the existing VQA system with object detection by providing a more reasonable and finer visual representation.

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。

↑