Denoising Task Routing for Diffusion Models

arXiv:2310.07138v2 Announce Type: replace
Abstract: Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL). Despite the inherent connection between diffusion models and MTL, there remains an unexplored area in designing neural architectures that explicitly incorporate MTL into the framework of diffusion models. In this paper, we present Denoising Task Routing (DTR), a simple add-on strategy for existing diffusion model architectures to establish distinct information pathways for individual tasks within …

abstract architectures arxiv cs.ai cs.cv denoising designing diffusion diffusion models framework generate images multi-task learning neural architectures process routing type