ScholarGate
助手
Machine learning

基于得分的生成模型

基于得分的生成模型由Yang Song和Stefano Ermon于2019年提出，并于2021年推广到随机微分方程（SDE）框架，它学习数据密度的梯度——即得分，而不是直接预测噪声，并利用得分生成新样本。它是将扩散模型统一在连续时间框架下的数学泛化。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

基于得分的生成模型
胶囊网络深度强化学习Neural ODE主成分分析变分自编码器扩散模型生成对抗网络

来源

  1. Song, Y. & Ermon, S. (2019). Generative Modeling by Estimating Gradients of the Data Distribution. NeurIPS 32, 11895–11907. link ↗
  2. Song, Y. et al. (2021). Score-Based Generative Modeling through Stochastic Differential Equations. ICLR. link ↗

如何引用本页

ScholarGate. (2026, June 1). Score-Based Generative Modeling through Stochastic Differential Equations. ScholarGate. https://scholargate.app/zh/deep-learning/score-based-diffusion

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

被引用于

扩散模型生成对抗网络变分自编码器

发现本页有问题？报告或提出修改建议 →

ScholarGate — Score-Based Generative Model (Score-Based Generative Modeling through Stochastic Differential Equations). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/score-based-diffusion · 数据集： https://doi.org/10.5281/zenodo.20539026