arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2611.06770cs.CV
收藏

城市管理中遥感的细粒度视觉推理基准测试

Benchmarking Fine-Grained Visual Reasoning for Remote Sensing in Urban Management

School of Electronics and Information Engineering, Harbin Institute of Technology(哈尔滨工业大学电子与信息工程学院);Huawei International PTE LTd(华为国际私人有限公司)

Jiawei Zhang, Rizhao Cai, Dayan Guan

AI总结:

本研究针对城市管理遥感的细粒度视觉推理,构建UMBench基准,发现现有MLLMs依赖场景先验忽略细粒度证据,提出无训练的证据优先思维链方法,可提升各类MLLMs在UMBench上的性能。

摘要:

细粒度视觉推理对城市管理中的遥感至关重要,但在多模态大语言模型(MLLMs)的评估中仍未得到充分探索。我们推出UMBench,这是一个基于无人机(UAV)图像构建的细粒度城市遥感基准,适用于交通监测、城市建设、环境质量和灾害预警等多项城市管理任务。对UMBench的评估显示,当前MLLMs常依赖场景级先验,忽略细粒度视觉证据。为解决此问题,我们进一步提出一种新颖的证据优先思维链方法,以无训练的方式引导模型检查细粒度视觉证据。实验表明,我们的方法可提升开源及商业MLLMs在UMBench上的性能。

英文摘要:

Fine-grained visual reasoning is essential for remote sensing in urban management, yet remains underexplored in the evaluation of multimodal large language models (MLLMs). We introduce UMBench, a fine-grained urban remote sensing benchmark built from unmanned aerial vehicle (UAV) images for multiple urban management tasks such as traffic monitoring, urban construction, environmental quality, and disaster warning. Evaluations on UMBench reveal that current MLLMs often rely on scene-level priors and overlook fine-grained visual evidence. To address this issue, we further propose a novel evidence-first chain-of-thought method that directs models to inspect fine-grained visual evidence in a training-free manner. Experiments show that our method can improve the performance of both open-source and commercial MLLMs on UMBench.

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。

↑