arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.16082cs.CVcs.LG
收藏

面向多域医学图像生成的扩散专家的 regime 感知路由器学习

Regime-Aware Router Learning for Multi-Domain Medical Image Generation with Diffusion Experts

Peng Cheng Laboratory(鹏城实验室);Southern University of Science and Technology(南方科技大学)

Yaoshuai Ma, Wei Yao, Yongxiang Liu, Feifan Wang, Da Chang, Pengxiang Xu, Shixun Zhang, Yonghong Tian

AI总结:

该研究针对多域医学图像生成的扩散模型,提出Server-Only和AD两种路由器学习策略,经实验验证AD策略可提升生成与路由性能,明确服务器数据可用性与专家性能是路由器学习的关键考量因素。

摘要:

异构医学图像数据催生了领域专用的扩散专家,但仅专家的专业化程度无法决定采样过程中如何组合它们的预测结果。当服务器拥有的图像有限且可能不具代表性时,学习全局路由器的挑战尤为突出。我们针对固定的专家池研究了两种路由器学习策略:仅服务器(Server-Only)从带有组件标签的服务器图像中学习依赖输入和时间步的专家分配;锚点-增量(Anchor-Delta,AD)使用相同的图像和冻结的专家,从去噪损失中获取额外证据,它将该证据与当前路由器的分配相结合以提炼目标,同时代理门控控制后续的细化步骤。组件标签描述数据来源,专家损失衡量经验预测性能。我们通过路由分析和配对医学图像生成来评估这些不同的信号。在异构四域设置中,经AD训练的路由器相比仅服务器的路由器提升了生成指标;一项单独的服务器数据研究显示,与修正路由的对比器相比,其在保留的路由任务上取得了增益;额外的配对评估表明,推理时证据混合的效果在不同基准间存在差异。这些发现确立了服务器数据可用性和专家性能是学习多域扩散模型路由器时需考虑的两个不同因素。

英文摘要:

Heterogeneous medical image data motivate domain-specialized diffusion experts, but expert specialization alone does not determine how their predictions should be combined during sampling. Learning a global router is particularly challenging when the server has limited, potentially unrepresentative images. We study two router-learning strategies for a fixed expert pool. Server-Only learns input- and timestep-dependent expert assignments from server images with component labels. Anchor-Delta (AD) uses the same images and frozen experts to obtain additional evidence from denoising losses. It distills targets that combine this evidence with the current router's assignments, while a proxy gate controls a subsequent refinement step. Component labels describe data origin; expert losses measure empirical prediction performance. We evaluate these distinct signals through routing analyses and paired medical image generation. An AD-trained router improves generation metrics over Server-Only in a heterogeneous four-domain setting, and a separate server-data study shows gains in held-out routing over a corrected-routing comparator. Additional paired evaluations show that the effect of inference-time evidence mixing varies across benchmarks. These findings establish server-data availability and expert performance as distinct considerations in learning routers for multi-domain diffusion models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑