DIA-RS${}^2$：Decoupled Information Alignment for Remote Sensing Reasoning Segmentation

Existing remote sensing image (RSI) reasoning segmentation methods follow the “Embedding-as-Mask” paradigm, directly transforming high-level semantic representations from multimodal large language models into mask prompts. However, we observe that, in complex RSI scenes with high visual load, target-related semantic responses are prone to spatial displacement. We hypothesize that this phenomenon may be related to the structural coupling inherent in the existing paradigm: a single special token simultaneously undertakes target semantic representation, visual evidence localization, and mask construction, leaving the mapping from language concepts to the visual space insufficiently and implicitly modeled. To examine this hypothesis, we conduct structural intervention experiments by modifying the token coupling scheme. The results show that explicitly modeling the mapping between language concepts and the visual space can significantly alleviate the degradation of vision-language correspondence as visual load increases, further supporting the association between the proposed structural bottleneck and semantic-visual misalignment. Inspired by these observations, we propose Decoupled Information Alignment for Remote Sensing Reasoning Segmentation (DIA-RS${}^2$). The method first enhances visual semantic queryability to construct a visual evidence space that is more amenable to concept querying. It then introduces an independent $⟨\mathrm{CON}⟩$ token together with a Concept-to-Evidence Adapter (CEA) to explicitly establish the correspondence between linguistic concepts and task-relevant visual regions. Subsequently, Evidence-guided Fusion (EGF) injects the retrieved visual evidence into $⟨\mathrm{SEG}⟩$, thereby enabling explicit alignment from linguistic concepts and visual evidence to mask prediction. Extensive experiments on multiple public benchmarks demonstrate that DIA-RS${}^2$ achieves more stable and significant performance improvements over existing baseline methods.