Fisher Information Improved Training-Free Conditional Diffusion Model

arXiv:2404.18252v1 Announce Type: new
Abstract: Recently, the diffusion model with the training-free methods has succeeded in conditional image generation tasks. However, there is an efficiency problem because it requires calculating the gradient with high computational cost, and previous methods make strong assumptions to solve it, sacrificing generalization. In this work, we propose the Fisher information guided diffusion model (FIGD). Concretely, we introduce the Fisher information to estimate the gradient without making any additional assumptions to reduce computation cost. Meanwhile, we …

abstract arxiv assumptions computational cost cs.cv diffusion diffusion model efficiency fisher free gradient however image image generation information solve tasks training type work