As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. The dataset and code are open-sourced under the Apache License 2.0 at https://github.com/AMAP-ML/SocioReasoner.

翻译：作为人类活动的枢纽，城市地表蕴含着丰富的语义实体。从卫星图像中分割这些多样的实体对于一系列下游应用至关重要。当前先进的语义分割模型能够可靠地分割由物理属性定义的实体（例如建筑物、水体），但在处理由社会属性定义的类别（例如学校、公园）时仍面临困难。在本研究中，我们通过视觉语言模型推理实现了社会语义分割。为此，我们引入了名为 SocioSeg 的城市社会语义分割数据集，这是一个包含卫星图像、数字地图以及按层级结构组织的社会语义实体像素级标签的新资源。此外，我们提出了一种名为 SocioReasoner 的新型视觉语言推理框架，该框架通过跨模态识别与多阶段推理来模拟人类识别和标注社会语义实体的过程。我们采用强化学习来优化这一不可微过程，并激发视觉语言模型的推理能力。实验证明，我们的方法相较于最先进的模型取得了性能提升，并展现出强大的零样本泛化能力。数据集与代码已在 Apache License 2.0 协议下开源，地址为 https://github.com/AMAP-ML/SocioReasoner。