发表机构
McMaster University; University of Waterloo; Western University（麦克马斯特大学; 滑铁卢大学; 西安大略大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出LoRSA框架，联合学习两类低秩分量实现生物医学视觉模型的参数高效微调，在乳腺密度分类任务中显著提升了模型对未见医学影像域的泛化性能。
AI 中文摘要
参数高效微调能够在有限计算资源下将视觉基础模型适配至生物医学任务，但单一低秩更新会将所有任务特定变化限制在一个狭窄的参数子空间中。这种限制可能导致模型无法同时表示全局共享的任务结构和泛化到未见成像域所需的局部残差方向。本文提出LoRSA，一种全局-残差适配框架，联合学习密集低秩分量和动态结构化稀疏低秩分量：密集分量捕获全局协调的任务适配，结构化分量提供互补的残差修正，其支撑集在训练过程中演变。我们对该分解的表示能力、近似特性、秩结构及奇异子空间互补性进行了表征。我们使用DINOv3-Base模型，以VinDr-Mammo作为源域、MammosighTR和RSNA作为未见外部域，对LoRSA进行四类乳腺密度分类评估。LoRSA在内部验证集上保持竞争力，并在两个目标数据集上取得最佳外部宏F1值：在MammosighTR上较最强竞争方法提升2.15个百分点，在RSNA上提升3.09个百分点。权重矩阵分析进一步显示，每个适配分量约92%的能量位于另一个分量的双边奇异子空间之外，表明两个分量学习到的更新方向在很大程度上互补。这些结果表明，将适配能力组织为不同的全局和残差路径可提升经参数高效微调的生物医学视觉模型的外部域泛化能力。
英文摘要
Parameter-efficient fine-tuning enables the adaptation of vision foundation models to biomedical tasks under limited computational resources, but a single low-rank update can constrain all task-specific changes to one narrow parameter subspace. This restriction may prevent the model from simultaneously representing globally shared task structure and localized residual directions required for generalization to unseen imaging domains. We introduce LoRSA, a global--residual adaptation framework that jointly learns a dense low-rank component and a dynamically structured-sparse low-rank component. The dense component captures globally coordinated task adaptation, while the structured component provides complementary residual corrections whose support evolves during training. We characterize the representational capacity, approximation properties, rank structure, and singular-subspace complementarity of this decomposition. We evaluate LoRSA for four-class breast-density classification using DINOv3-Base, with VinDr-Mammo as the source domain and MammosighTR and RSNA as unseen external domains. LoRSA remains competitive on the internal validation set and achieves the best external macro-F1 on both target datasets, improving upon the strongest competing method by 2.15 percentage points on MammosighTR and 3.09 percentage points on RSNA. Weight-matrix analysis further shows that approximately $92\%$ of the energy of each adaptation component lies outside the bilateral singular subspace of the other, indicating that the two components learn largely complementary update directions. These results suggest that organizing adaptation capacity into distinct global and residual paths can improve the external-domain generalization of parameter-efficiently adapted biomedical vision models.
