DisasterInsight: 一种多模态基准，用于功能感知和基于事实的灾害评估
DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response
AI总结：
DisasterInsight提出一种多模态基准，用于评估视觉-语言模型在灾害分析任务中的性能，通过DI-Chat模型在损害识别和报告生成方面取得显著提升。
摘要：
及时解读卫星影像对灾害响应至关重要，但现有的遥感视觉-语言基准大多专注于粗略标签和图像级识别，忽略了人道主义工作流程中所需的功能理解及指令鲁棒性。我们引入DisasterInsight，一种多模态基准，旨在评估视觉-语言模型（VLMs）在真实灾害分析任务上的能力。DisasterInsight将xBD数据集重构为约112万栋建筑为中心的实例，并支持在多个任务上的指令多样化评估，包括建筑功能分类、损害等级和灾害类型分类、计数以及符合人道主义评估指南的结构化报告生成。为了建立领域适应的基线，我们提出DI-Chat，通过在灾害特定指令数据上对现有VLM骨干网络进行参数高效的低秩适应（LoRA）进行微调获得。在对最先进的通用和遥感VLMs进行广泛实验后，发现各任务间存在显著性能差距，尤其是在损害理解和结构化报告生成方面。DI-Chat在损害等级和灾害类型分类以及报告生成质量上实现了显著提升，而建筑功能分类对所有评估模型来说仍具有挑战性。DisasterInsight为研究灾害影像中的基于事实的多模态推理提供了统一的基准。
英文摘要：
Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-centric assessment. To study this building-centric gap, we introduce \method{}, a diagnostic benchmark built on xBD, a pre/post-disaster satellite dataset with building-level damage labels. \method{} enriches building instances with OpenStreetMap-derived functional labels and contains 134{,}108 task-specific instruction records across 15 task types, spanning instance-level assessment, scene-level counting, multi-instance reasoning, and structured report generation. The benchmark supports RGB pre/post-disaster imagery, single- and multi-view instance formulations, and scene-level RGB/SAR diagnostic inputs. Experiments with general-domain and remote-sensing VLMs show that models perform better on visible damage cues than on building-function understanding, multi-instance reasoning, counting, and grounded reporting. Instruction tuning improves performance on several tasks but does not close this building-centric gap.
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。
