arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02600cs.LGcs.CV
收藏

生成扩散模型的噪声估计

Noise Estimation for Generative Diffusion Models

Tel-Aviv University(特拉维夫大学);Facebook AI Research(Facebook人工智能研究院)

Robin San-Roman, Eliya Nachmani, Lior Wolf

摘要:

生成扩散模型已经成为语音和图像生成中的主要模型。然而,为了用少量的去噪步骤来良好地执行,需要对噪声参数集进行昂贵的调谐。在这项工作中,我们提出了一个简单而通用的学习方案,可以逐步调整这些噪声参数,对于任何给定的步骤数,而以前的工作需要分别为每个数字重新调整。此外,在不修改扩散模型的权重的情况下,我们能够显著地改善合成结果,对于少量的步骤。我们的方法来在一个可以忽略不计的计算成本。

英文摘要:

Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning of the set of noise parameters is needed. In this work, we present a simple and versatile learning scheme that can step-by-step adjust those noise parameters, for any given number of steps, while the previous work needs to retune for each number separately. Furthermore, without modifying the weights of the diffusion model, we are able to significantly improve the synthesis results, for a small number of steps. Our approach comes at a negligible computation cost.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑