通过混合分布得分估计，简单训练一步生成模型。
Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions
- 用多噪声水平的混合分布得分来优化生成模型。
- 在CIFAR-10和ImageNet上性能媲美甚至超越现有方法。
- 无需调参、训练稳定，适合从零训练或模型蒸馏。
我们提出一种名为得分混合训练（SMT）的新框架，通过最小化一类称为α-偏斜杰恩斯-申农散度的差异来训练一步生成模型。核心思想是在多个噪声水平下估计真实与虚假样本混合分布的得分。与一致性模型类似，该方法既支持从头训练（SMT），也支持使用预训练扩散模型进行蒸馏，称为得分混合蒸馏（SMD）。实现简单，几乎无需超参数调整，且训练过程稳定。在CIFAR-10和ImageNet 64x64上的实验表明，SMT/SMD在性能上具有竞争力，甚至优于现有方法。
原文摘要 · Abstract (English)
We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models by minimizing a class of divergences called the $α$-skew Jensen--Shannon divergence. At its core, SMT estimates the score of mixture distributions between real and fake samples across multiple noise levels. Similar to consistency models, our approach supports both training from scratch (SMT) and distillation using a pretrained diffusion model, which we call Score-of-Mixture Distillation (SMD). It is simple to implement, requires minimal hyperparameter tuning, and ensures stable training. Experiments on CIFAR-10 and ImageNet 64x64 show that SMT/SMD are competitive with and can even outperform existing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。