arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.07045cs.CVcs.AI
收藏

VLRS-Bench: 一种面向遥感的视觉-语言推理基准

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing

School of Computer Science, Wuhan University(武汉大学计算机学院)

Zhiming Luo, Hebaixu Wang, Haonan Guo, Jing Zhang, Bo Du

AI总结:

本文提出VLRS-Bench,首个专注于复杂遥感推理的基准,包含2000个问题-答案对,涵盖14项任务和八个时间阶段,揭示现有MLLM在遥感任务中的瓶颈。

摘要:

近年来,多模态大语言模型(MLLMs)的进步使复杂推理成为可能。然而,现有遥感(RS)基准严重偏向感知任务,如物体识别和场景分类,限制了MLLM在认知需求高的遥感应用中的发展。为此,我们提出了视觉-语言推理基准(VLRS-Bench),这是首个专门针对复杂遥感推理的基准。VLRS-Bench在认知、决策和预测三个核心维度上结构化,包含2000个问题-答案对,平均问题长度为130.19词,涵盖14项任务和最多八个时间阶段。VLRS-Bench通过专门的管道整合遥感特定先验知识和专家知识,确保地理空间真实性和推理复杂性。实验结果揭示了现有最先进MLLM在遥感任务中的显著瓶颈,为推动遥感社区的多模态推理发展提供了关键见解。项目仓库可在https://github.com/MiliLab/VLRS-Bench获取。

英文摘要:

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,000 question-answer pairs with an average question length of 129.87 words, spanning 14 tasks and up to eight temporal phases. VLRS-Bench is constructed via a specialized pipeline that integrates RS-specific priors and expert knowledge to ensure geospatial realism and reasoning complexity. Experimental results reveal significant bottlenecks in existing state-of-the-art MLLMs, providing critical insights for advancing multimodal reasoning within the remote sensing community.

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。

↑