通过双尺度互蒸馏，实现医疗影像分割的高效联邦学习。
DSFedMed: Dual-Scale Federated Medical Image Segmentation via Mutual Distillation Between Foundation and Lightweight Models
- 用基础模型与轻量客户端互相蒸馏知识
- Dice分数平均提升2%，通信与推理成本降90%
- 适合资源受限的医疗联邦学习场景
基础模型（FMs）在多种视觉任务中展现出强大泛化能力，但在联邦设置下受限于高计算开销、大通信成本和高昂推理代价。本文提出DSFedMed，一种双尺度联邦框架，通过中心化基础模型与轻量级客户端模型之间的相互知识蒸馏，实现医学图像分割。为支持蒸馏，生成一组高质量医疗图像以替代真实公开数据集，并提出可学习性引导的样本选择策略，提升双尺度蒸馏的效率与效果。该互蒸馏机制使基础模型将通用知识传递给客户端，同时融合客户端特定信息以优化基础模型。在五个医学影像分割数据集上的评估显示，相比现有联邦基础模型基线，DSFedMed平均提升2% Dice分数，通信成本和推理时间降低近90%。结果表明该方法在资源受限的联邦部署中具有显著效率优势与可扩展性。
原文摘要 · Abstract (English)
Foundation Models (FMs) have demonstrated strong generalization across diverse vision tasks. However, their deployment in federated settings is hindered by high computational demands, substantial communication overhead, and significant inference costs. We propose DSFedMed, a dual-scale federated framework that enables mutual knowledge distillation between a centralized foundation model and lightweight client models for medical image segmentation. To support knowledge distillation, a set of high-quality medical images is generated to replace real public datasets, and a learnability-guided sample selection strategy is proposed to enhance efficiency and effectiveness in dual-scale distillation. This mutual distillation enables the foundation model to transfer general knowledge to lightweight clients, while also incorporating client-specific insights to refine the foundation model. Evaluations on five medical imaging segmentation datasets show that DSFedMed achieves an average 2 percent improvement in Dice score while reducing communication costs and inference time by nearly 90 percent compared to existing federated foundation model baselines. These results demonstrate significant efficiency gains and scalability for resource-limited federated deployments.
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。