论文标题
非均匀扩散模型
Non-Uniform Diffusion Models
论文作者
论文摘要
扩散模型已成为深层生成建模的最有希望的框架之一。在这项工作中，我们探讨了不均匀扩散模型的潜力。我们表明，非均匀扩散会导致多尺度扩散模型，这些模型与多尺度归一化流的结构相似。我们在实验上发现，在相同或更少的训练时间中，多尺度扩散模型比标准均匀扩散模型获得更好的FID得分。更重要的是，它生成样品$ 4.4 $ 4.4 $ $ $乘以$ 128 \ times 128 $分辨率。在使用更多量表的较高分辨率中，预计加速度将更高。此外，我们表明，不均匀的扩散会导致有条件得分函数的新估计量，该估计函数通过最新的条件降解估计量以PAR性能达到了PAR性能。我们的理论和实验发现伴随着开源库MSDIFF，该图书馆可以促进对非均匀扩散模型的进一步研究。
Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows. We experimentally find that in the same or less training time, the multi-scale diffusion model achieves better FID score than the standard uniform diffusion model. More importantly, it generates samples $4.4$ times faster in $128\times 128$ resolution. The speed-up is expected to be higher in higher resolutions where more scales are used. Moreover, we show that non-uniform diffusion leads to a novel estimator for the conditional score function which achieves on par performance with the state-of-the-art conditional denoising estimator. Our theoretical and experimental findings are accompanied by an open source library MSDiff which can facilitate further research of non-uniform diffusion models.
