弥合语义与几何：一种解耦的LVLM-SAM框架用于光学遥感中的推理分割
Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing
AI总结：
本文提出解耦的LVLM-SAM框架，通过结构化几何提示优化，提升光学遥感中推理分割的性能，实现语义与几何的结合。
摘要：
大型视觉-语言模型（LVLMs）在推动光学遥感（RS）分析方面具有巨大潜力，但现有推理分割框架通过端到端监督微调耦合语言推理和像素预测，导致几何接地薄弱且任务泛化受限。为此，我们开发了Think2Seg-RS，一种解耦框架，通过训练LVLM提示器控制冻结的Segment Anything Model（SAM）以进行结构化几何提示。通过仅基于最终掩码IoU的掩码-only Group Relative Policy Optimization（GRPO）强化学习目标，LVLM学会将抽象语义推理转化为空间上扎根的动作，在EarthReason数据集上达到最先进的性能。值得注意的是，Think2Seg-RS在EarthReason数据集上优于RemoteReasoner和SegEarth-R1等方法，测试cIoU达到75.60%，gIoU达到73.36%，分别比最强基线提升6.47%和2.40%。在三个指称分割基准上的零样本评估揭示了任务归纳偏置的根本区别，暴露了语义级接地与实例级任务之间的明显分歧。我们进一步发现，在语义级监督下，紧凑分割器通过缓解纹理过度分割优于更大分割器，并且在异质航空背景中，无约束的负提示不稳定性。这些发现表明，通过直接分割反馈优化LVLMs提供了一种可扩展的复杂地理空间推理框架，有效弥合了抽象语言理解和精确像素级执行之间的差距。
英文摘要：
Large Vision--Language Models (LVLMs) hold great promise for advancing optical remote sensing (RS) analysis, yet existing reasoning segmentation frameworks couple linguistic reasoning and pixel prediction through end-to-end supervised fine-tuning, leading to weak geometric grounding and limited generalization across tasks. To address this, we developed Think2Seg-RS, a decoupled framework that trains an LVLM prompter to control a frozen Segment Anything Model (SAM) via structured geometric prompts. Through a mask-only Group Relative Policy Optimization (GRPO) reinforcement learning objective driven strictly by final mask IoU, the LVLM learns to translate abstract semantic reasoning into spatially grounded actions, achieving state-of-the-art performance on the EarthReason dataset. Notably, Think2Seg-RS outperforms leading approaches such as RemoteReasoner and SegEarth-R1 on the EarthReason dataset by reaching a test cIoU of 75.60% and gIoU of 73.36%, yielding absolute improvements of 6.47% and 2.40% over the strongest baseline, respectively. Zero-shot evaluations across three referring segmentation benchmarks reveal a fundamental distinction in task inductive bias, exposing a distinct divide between semantic-level grounding -- which aggregates all regions matching a conceptual intent -- and instance-level tasks that demand discrete object separation. We further found that compact segmenters outperform larger ones under semantic-level supervision by mitigating textural over-segmentation, and that unconstrained negative prompting is unstable in heterogeneous aerial backgrounds. Together, these findings demonstrate that optimizing LVLMs through direct segmentation feedback offers a scalable framework for complex geospatial reasoning, effectively bridging the gap between abstract language understanding and precise pixel-level execution.
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。
