发表机构
Wuhan University（武汉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对遥感域偏移下预训练模型低秩适配的子空间失配问题，提出域感知松弛正交子空间适配（DROS），通过数据条件子空间学习与松弛正交变换实现高效适配，并扩展至多模态，在多个遥感基准上达到最优性能。
AI 中文摘要
预训练基础模型（FMs）在计算机视觉领域取得了显著成功，但其高昂的微调成本限制了实际部署。参数高效微调（PEFT）方法，如低秩适配（LoRA），通过将更新约束在预定义的低秩子空间内来提高效率。然而，当应用于具有显著域偏移的遥感任务时，固定子空间是在未观察下游激活分布的情况下构建的，因此可能为适配提供较差的坐标系，这一现象在此被称为子空间失配。为解决此问题，引入了一个统一框架，称为域感知松弛正交子空间适配（DROS），该框架将低秩适配重新表述为数据条件子空间学习和灵活的子空间适配。具体而言，权重分解以从下游训练分布估计的二阶激活统计为条件，使得初始化反映遥感数据实际诱导的特征几何，随后通过松弛正交参数化实现灵活的几何变换。此外，该框架通过跨模态特定子空间共享变换结构扩展到多模态设置（MM-DROS），促进高效的跨模态交互。在多个遥感基准上的大量实验表明，DROS实现了最先进的性能，甚至超越了全量微调，且无额外推理开销。
英文摘要
Pretrained foundation models (FMs) have achieved remarkable success in computer vision, yet their high fine-tuning cost limits practical deployment. Parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) improve efficiency by constraining updates to a predefined low-rank subspace. However, when applied to remote sensing tasks with substantial domain shifts, the fixed subspace is constructed without observing the downstream activation distribution and can therefore provide a poor coordinate system for adaptation, a phenomenon herein termed subspace mismatch. To address this issue, a unified framework is introduced, termed Domain-aware Relaxed Orthogonal Subspace adaptation (DROS), which reformulates low-rank adaptation as data-conditioned subspace learning and flexible subspace adaptation. Specifically, the weight decomposition is conditioned on second-order activation statistics estimated from the downstream training distribution, so that the initialization reflects the feature geometry actually induced by the remote-sensing data, followed by flexible geometric transformations enabled by a relaxed orthogonal parameterization. Furthermore, the framework is extended to multimodal settings (MM-DROS) by sharing transformation structures across modality-specific subspaces, facilitating efficient cross-modal interaction. Extensive experiments on multiple remote sensing benchmarks demonstrate that DROS achieves state-of-the-art performance, even surpassing full fine-tuning, without additional inference overhead.
