遥感基础模型：面向目标定位的多模态大语言模型分析
Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization
AI总结：
本研究分析近期具备细粒度空间推理能力的多模态大语言模型（MLLMs），在地球观测（EO）目标定位任务上进行基准测试，发现其在特定场景下适合零样本任务，并提供提示词选择等优化方向，为EO定位任务的MLLM应用提供参考。
摘要：
多模态大语言模型（MLLMs）改变了计算机视觉的格局，在各类任务中取得了令人瞩目的成果，尤其是在零样本场景下。但遗憾的是，其优异性能并非总能迁移到分布外领域，如地球观测（EO）影像。此前研究表明，MLLMs在部分EO任务（如图像描述、场景理解）上表现出色，但在需要更细粒度空间推理的任务（如目标定位）上表现不佳。然而MLLMs发展迅速，旧有见解易过时。本研究分析了近期明确训练以具备细粒度空间推理能力的MLLMs，在EO目标定位任务上对其进行基准测试。结果显示这些模型在特定场景下性能良好，适合零样本场景。此外，本研究还详细讨论了提示词选择、地面采样距离（GSD）优化及失败案例分析。希望本研究能为其他研究者评估MLLM是否适合特定EO定位任务及如何优化提供参考。
英文摘要：
Multimodal large language models (MLLMs) have altered the landscape of computer vision, obtaining impressive results across a wide range of tasks, especially in zero-shot settings. Unfortunately, their strong performance does not always transfer to out-of-distribution domains, such as earth observation (EO) imagery. Prior work has demonstrated that MLLMs excel at some EO tasks, such as image captioning and scene understanding, while failing at tasks that require more fine-grained spatial reasoning, such as object localization. However, MLLMs are advancing rapidly and insights quickly become out-dated. In this work, we analyze more recent MLLMs that have been explicitly trained to include fine-grained spatial reasoning capabilities, benchmarking them on EO object localization tasks. We demonstrate that these models are performant in certain settings, making them well suited for zero-shot scenarios. Additionally, we provide a detailed discussion focused on prompt selection, ground sample distance (GSD) optimization, and analyzing failure cases. We hope that this work will prove valuable as others evaluate whether an MLLM is well suited for a given EO localization task and how to optimize it.
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。
