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

arXiv:2610.16082v1 Announce Type: new Abstract: 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.

Related

• Synthetic Leprosy Image Generation Using Mask-Conditioned Latent Diffusion and Transfer Learning from Large Chronic Wound Datasets
• Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model
• Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA

Source: arXiv cs.CV | 2026-10-14