Efficient Denoising using Score Embedding in Score-based Diffusion Models

arXiv:2404.06661v1 Announce Type: new
Abstract: It is well known that training a denoising score-based diffusion models requires tens of thousands of epochs and a substantial number of image data to train the model. In this paper, we propose to increase the efficiency in training score-based diffusion models. Our method allows us to decrease the number of epochs needed to train the diffusion model. We accomplish this by solving the log-density Fokker-Planck (FP) Equation numerically to compute the score \textit{before} training. …

abstract arxiv cs.cv data denoising diffusion diffusion models efficiency embedding image image data paper train training type