CrossEarth-Gate：面向跨域遥感语义分割高效适配的 Fisher 引导自适应调优引擎
CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation
把 Fisher 信息当作模块重要性的度量，在空间/语义/频率三类适配模块组成的工具箱上做动态稀疏激活，为视觉基础模型跨域适配提供了一种可复用的「按梯度流贡献选模块」的 PEFT 思路，可直接迁移到其他密集预测任务的域偏移场景。
原文依据 Fisher-guided adaptive selection mechanism that operates on this toolbox
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在遥感领域，参数高效微调已成为激活基础模型下游任务泛化表征能力的关键途径。然而，现有专用参数高效微调方法在应用于大规模对地观测任务时往往失效，因为它们无法充分应对遥感数据中固有的多方面且不可预测的域间差异（例如空间、语义与频率偏移）。为克服这一问题，我们提出 CrossEarth-Gate，包含两项主要贡献。第一，我们构建了一个全面的遥感模块工具箱以应对多方面的域间差异，由空间、语义与频率模块组成。第二，我们在该工具箱之上开发了一种 Fisher 引导的自适应选择机制。该选择以 Fisher 信息为指导，通过度量各模块对任务特定梯度流的贡献来量化其重要性。它动态地仅在合适的层激活最关键的模块，引导梯度流以最大化适配的有效性与效率。大量实验验证了本方法的有效性与泛化性，CrossEarth-Gate 在 18 个遥感语义分割跨域基准中的 16 个上取得了最优性能。
英文原文摘要 1301 字符
In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (e.g., spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance on 16 out of 18 cross-domain benchmarks for RS semantic segmentation.