AI 中文总结
本文针对遥感大视觉语言模型高分辨率处理效率低的问题，提出SA-GEM即插即用剪枝框架，通过尺度自适应与地理空间证据调制实现效率与精度提升，在XLRS-Bench上超GeoLLaVA-8K 2.3%且推理提速2.4倍。
AI 中文摘要
遥感大视觉语言模型（RS-LVLM）已在地球观测图像的多模态理解方面取得进展，但其性能受限于高分辨率处理：视觉令牌数量随输入分辨率线性增长呈二次方增加，而重要视觉证据本质上是稀疏的，且在扩展序列中被逐渐稀释。现有令牌剪枝方法大多依赖与尺度无关的分辨率策略和孤立的重要性线索，限制了任务对齐的粒度自适应与整体证据保留。为解决该问题，本文提出Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning（SA-GEM，尺度自适应与地理空间证据调制型令牌剪枝），这是一种即插即用框架，统一了任务自适应令牌粒度分配与整体地理空间令牌重要性调制。具体而言，轻量级路由器根据查询依赖的令牌粒度选择分辨率，令牌重要性调制器联合建模任务相关性、空间结构与局部冗余，以保留整体地理空间证据。研究表明，更高分辨率并非普遍有益，达到足够粒度后，令牌质量比令牌数量更重要。在多个基准上的实验显示，SA-GEM相比现有剪枝方法在准确性和效率上均实现持续提升；在XLRS-Bench上，其准确性超过GeoLLaVA-8K 2.3%，总推理速度提升2.4倍。
英文摘要
RS-LVLMs have advanced multimodal understanding of Earth observation imagery, yet their performance is fundamentally constrained by high-resolution processing, as visual token counts grow quadratically with linear input resolution while important visual evidence is inherently sparse and increasingly diluted across the expanded sequence. Existing token pruning methods largely rely on scale-agnostic resolution policies and isolated importance cues, limiting task-aligned granularity adaptation and holistic evidence preservation. To address this, we present Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning (SA-GEM), a plug-and-play framework that unifies task-adaptive token granularity allocation with holistic geospatial token importance modulation. Specifically, a lightweight router selects the resolution based on query-dependent token granularity, while a token importance modulator jointly models task relevance, spatial structure, and local redundancy to preserve holistic geospatial evidence. We show that higher resolution is not universally beneficial and, once sufficient granularity is reached, token quality matters more than token quantity. Experiments across various benchmarks demonstrate that SA-GEM achieves consistent gains in both accuracy and efficiency over existing pruning methods. On XLRS-Bench, it surpasses GeoLLaVA-8K by 2.3% in accuracy with a 2.4 times total inference speedup.
