arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.09016cs.LGcs.AIcs.CV
收藏

生成扩散模型的理论研究:综述

Theoretical research on generative diffusion models: an overview

Yıldız Technical University(伊兹迪兹技术大学)

Melike Nur Yeğin, Mehmet Fatih Amasyalı

AI总结:

本文综述生成扩散模型的理论进展,将其方法分为训练与采样两类,为未来研究提供清晰分类框架。

摘要:

生成扩散模型凭借其强大的理论基础,在许多领域取得了巨大成功。它们将数据分布转换为噪声,再去除噪声以恢复相似的分布。许多现有综述侧重于特定应用领域,而未关注算法本身的研究。与它们不同,我们研究了生成扩散模型的理论发展。这些方法主要分为两类:基于训练的和基于采样的。认识到这一点,使我们能够为未来将进行新研究的研究者提供一个清晰且易于理解的分类。

英文摘要:

Generative diffusion models showed high success in many fields with a powerful theoretical background. They convert the data distribution to noise and remove the noise back to obtain a similar distribution. Many existing reviews focused on the specific application areas without concentrating on the research about the algorithm. Unlike them we investigated the theoretical developments of the generative diffusion models. These approaches mainly divide into two: training-based and sampling-based. Awakening to this allowed us a clear and understandable categorization for the researchers who will make new developments in the future.

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。

↑