BriefGPT.xyz
Feb, 2023
一致性扩散模型：通过学习一致性来缓解采样漂移
Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent
HTML
PDF
Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis
TL;DR
提出基于一致性约束的得分匹配方法，实验结果表明得到了CIFAR-10中条件和无条件生成的最新成果和AFHQ以及FFHQ的基准改进。
Abstract
Imperfect
score-matching
leads to a shift between the training and the sampling distribution of
diffusion models
. Due to the recursive nature of the generation process, errors in previous steps yield sampling ite
→