GeoSeg: 无需训练的推理驱动遥感图像分割
GeoSeg: Training-Free Reasoning-Driven Segmentation in Remote Sensing Imagery
AI总结：
GeoSeg通过结合大规模语言模型推理与精确定位，无需训练实现遥感图像分割的高效解决方案。
摘要：
最近在大规模语言模型（MLLMs）中的进展正在将分割从固定类别的预测重新定义为基于指令的定位。虽然基于推理的分割在自然场景中取得了快速进展，但遥感图像由于推理导向数据的高昂成本和特定领域的挑战，如俯视视角，缺乏通用的解决方案。我们提出了GeoSeg，一种零样本、无需训练的框架，以绕过推理驱动遥感分割的监督瓶颈。GeoSeg通过将大规模语言模型的推理与精确定位相结合，采用：(i) 偏差感知的坐标细化以纠正系统性的定位偏移，以及 (ii) 双路由提示机制将语义意图与细粒度空间线索融合。我们还引入了GeoSeg-Bench，一个包含810个图像-查询对的诊断基准，具有分层难度级别。实验表明，GeoSeg在所有基线方法上均表现优异，广泛的消融实验证实了每个组件的有效性和必要性。
英文摘要：
Recent advances in MLLMs are reframing segmentation from fixed-category prediction to instruction-grounded localization. While reasoning based segmentation has progressed rapidly in natural scenes, remote sensing lacks a generalizable solution due to the prohibitive cost of reasoning-oriented data and domain-specific challenges like overhead viewpoints. We present GeoSeg, a zero-shot, training-free framework that bypasses the supervision bottleneck for reasoning-driven remote sensing segmentation. GeoSeg couples MLLM reasoning with precise localization via: (i) bias-aware coordinate refinement to correct systematic grounding shifts and (ii) a dual-route prompting mechanism to fuse semantic intent with fine-grained spatial cues. We also introduce GeoSeg-Bench, a diagnostic benchmark of 810 image--query pairs with hierarchical difficulty levels. Experiments show that GeoSeg consistently outperforms all baselines, with extensive ablations confirming the effectiveness and necessity of each component.
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。
