超越U：加速和轻量化扩散模型

摘要

扩散模型是一类生成模型，在诸如图像合成、视频生成和分子设计等任务中取得了创纪录的性能。尽管具备这些能力，其效率，特别是在逆去噪过程中，仍然面临着慢收敛速度和高计算成本的挑战。在这项工作中，我们提出了一种利用连续动力系统来设计新型去噪网络的方法，用于扩散模型，该方法更具参数效率，收敛速度更快，并且表现出更强的噪声鲁棒性。通过对去噪概率扩散模型进行实验，我们的框架与去噪扩散概率模型（DDPMs）中标准U-Net相比，参数约为四分之一，浮点运算（FLOPs）约为30%。此外，我们的模型在相同条件下推断速度比基准模型快高达70%，同时收敛到更优质的解决方案。

English

Diffusion models are a family of generative models that yield record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse denoising process, remains a challenge due to slow convergence rates and high computational costs. In this work, we introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models that is more parameter-efficient, exhibits faster convergence, and demonstrates increased noise robustness. Experimenting with denoising probabilistic diffusion models, our framework operates with approximately a quarter of the parameters and 30% of the Floating Point Operations (FLOPs) compared to standard U-Nets in Denoising Diffusion Probabilistic Models (DDPMs). Furthermore, our model is up to 70% faster in inference than the baseline models when measured in equal conditions while converging to better quality solutions.

超越U：加速和轻量化扩散模型

Beyond U: Making Diffusion Models Faster & Lighter

摘要

Support