SegEarth-R2：面向遥感图像的综合语言引导分割
SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images
面向遥感场景的语言引导分割，用 MLLM 直接输出分割结果；其空间注意力监督机制可迁移到小目标与部件级定位任务，灵活的分割查询机制为单目标/多目标统一建模提供了可复用设计。
原文依据 we present LaSeRS, the first large-scale dataset built for comprehensive training and evaluation across four critical dimensions of language-guided segmentation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论将复杂语言有效定位到遥感（RS）图像的像素上，是灾害响应与环境监测等应用中的关键挑战。现有模型能够解析简单的单目标指令，但在面对复杂地理空间场景时表现不佳，例如分割不同粒度的目标、执行多目标指令以及理解隐含的用户意图。为针对这些失败推动进展，我们提出 LaSeRS，这是首个大规模数据集，围绕语言引导分割的四个关键维度构建，用于全面训练与评估：层级粒度、目标多重性、推理需求以及语言多样性。通过覆盖这些维度，LaSeRS 超越了简单指令，为复杂地理空间推理提供了基准。这填补了一个关键空白：现有数据集过度简化，导致真实世界模型容易敏感。我们还提出 SegEarth-R2，一种面向遥感综合语言引导分割的 MLLM 架构，直接应对上述挑战。该模型的有效性源于两项关键改进：（1）空间注意力监督机制，专门处理小目标及其部件的定位；（2）灵活高效的分割查询机制，可同时处理单目标与多目标场景。实验结果表明，SegEarth-R2 在 LaSeRS 及其他基准上取得了出色性能，为下一代地理空间分割建立了强大的基线。所有数据与代码将公开。
英文原文摘要 1652 字符
Effectively grounding complex language to pixels in remote sensing (RS) images is a critical challenge for applications like disaster response and environmental monitoring. Current models can parse simple, single-target commands but fail when presented with complex geospatial scenarios, e.g., segmenting objects at various granularities, executing multi-target instructions, and interpreting implicit user intent. To drive progress against these failures, we present LaSeRS, the first large-scale dataset built for comprehensive training and evaluation across four critical dimensions of language-guided segmentation: hierarchical granularity, target multiplicity, reasoning requirements, and linguistic variability. By capturing these dimensions, LaSeRS moves beyond simple commands, providing a benchmark for complex geospatial reasoning. This addresses a critical gap: existing datasets oversimplify, leading to sensitivity-prone real-world models. We also propose SegEarth-R2, an MLLM architecture designed for comprehensive language-guided segmentation in RS, which directly confronts these challenges. The model's effectiveness stems from two key improvements: (1) a spatial attention supervision mechanism specifically handles the localization of small objects and their components, and (2) a flexible and efficient segmentation query mechanism that handles both single-target and multi-target scenarios. Experimental results demonstrate that our SegEarth-R2 achieves outstanding performance on LaSeRS and other benchmarks, establishing a powerful baseline for the next generation of geospatial segmentation. All data and code will be released.