基于分数的扩散模型中条件作用的插件式解释
A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models
浏览论文内容
中文总结 AI 辅助
该研究提出基于多速度联合扩散的插件式条件机制，推导相关SDE与ODE并引入对数福克-普朗克残差正则化，在条件图像生成任务中验证了方法的有效性。
中文摘要 AI 辅助
我们提出了一种扩散模型的条件机制，该机制基于目标与条件的多速度联合扩散。该机制学习一个无条件联合得分网络，并在推理阶段通过插件式校正项来施加条件。插件式项将条件贡献与学习到的无条件动力学分离，为条件如何引导目标分布的生成提供了透明视角。在此基础上，我们推导了显式的条件反向时间随机微分方程（SDE）和近似概率流常微分方程（ODE），从而实现了有原则且可直接比较的条件采样器。为减少由此产生的ODE-SDE差异，我们引入了对数福克-普朗克残差正则化，以提升ODE采样质量。在条件图像生成任务上的实验表明，该方法具有竞争力的性能，支持插件式条件作用视角的有效性；额外的ODE-SDE对比实验显示，对数福克-普朗克残差正则化可提升确定性ODE采样的效果。
英文摘要
We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at inference via a plug-in correction term. The plug-in term separates the conditioning contribution from the learned unconditional dynamics, offering a transparent view of how the condition steers generation of the target distribution. Building on this, we derive explicit conditional reverse-time SDEs and approximate probability-flow ODEs, enabling principled and directly comparable conditional samplers. To reduce the induced ODE--SDE discrepancy, we introduce a log-Fokker--Planck residual regularization that improves ODE sampling quality. Experiments on conditional image generation tasks demonstrate competitive performance and support the effectiveness of the plug-in conditioning view. Additional ODE--SDE comparison experiments show that the log-Fokker--Planck residual regularization improves deterministic ODE sampling.
发表机构
- International Institute of Information Technology Hyderabad（国际信息技术学院海得拉巴分校）
- University of Bath（巴斯大学）
机构由 AI 辅助整理，请以论文原文为准。
