SALT通过选择性调整关键奇异值，实现高效医疗图像分割微调。
SALT: Parameter-Efficient Fine-Tuning via Singular Value Adaptation with Low-Rank Transformation
- 仅用3.9%可训练参数，结合低秩更新与关键奇异值调节
- 在20到1000样本的5个医学数据集上提升Dice 2%~5%
- 适合资源有限但需高精度分割的医学视觉任务
医学图像分割需要模型捕捉细致的领域特异性特征。尽管大型基础模型具备高度灵活性，但其微调成本高昂。参数高效微调（PEFT）方法如低秩适应（LoRA）通过低秩矩阵高效更新权重，但在秩过低时易出现欠拟合；而基于完整奇异值分解（SVD）的方法虽能全面更新，却缺乏灵活性且跨数据集表现不一。我们提出SALT（奇异值自适应与低秩变换），通过可训练缩放和偏移参数选择性调节最具影响力的奇异值，同时对剩余子空间进行低秩更新。该混合方法融合了LoRA与SVD的优势，在不增加模型大小或深度的前提下实现有效适配。在涵盖20至1000样本的5个挑战性医学数据集上，SALT相比现有先进PEFT方法（LoRA与SVD）在Dice分数上提升2%至5%，仅使用3.9%的可训练参数，展现出在低资源环境下的鲁棒适应能力。SALT代码已开源：https://github.com/BioMedIA-MBZUAI/SALT
原文摘要 · Abstract (English)
The complex nature of medical image segmentation calls for models that are specifically designed to capture detailed, domain-specific features. Large foundation models offer considerable flexibility, yet the cost of fine-tuning these models remains a significant barrier. Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), efficiently update model weights with low-rank matrices but may suffer from underfitting when the chosen rank is insufficient to capture domain-specific nuances. Conversely, full-rank Singular Value Decomposition (SVD) based methods provide comprehensive updates by modifying all singular values, yet they often lack flexibility and exhibit variable performance across datasets. We propose SALT (Singular Value Adaptation with Low-Rank Transformation), a method that selectively adapts the most influential singular values using trainable scale and shift parameters while complementing this with a low-rank update for the remaining subspace. This hybrid approach harnesses the advantages of both LoRA and SVD, enabling effective adaptation without relying on increasing model size or depth. Evaluated on 5 challenging medical datasets, ranging from as few as 20 samples to 1000, SALT outperforms state-of-the-art PEFT (LoRA and SVD) by 2% to 5% in Dice with only 3.9% trainable parameters, demonstrating robust adaptation even in low-resource settings. The code for SALT is available at: https://github.com/BioMedIA-MBZUAI/SALT
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。