Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of $N$-step teacher sampler with $N/2$-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed \textbf{C}lassifier-based \textbf{F}eature \textbf{D}istillation (CFD). Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is provided at \url{https://github.com/zju-SWJ/RCFD}.

翻译：虽然扩散模型显示出产生质量高于GANs的图像的巨大潜力,但缓慢的采样速度阻碍了其广泛应用。因此,建议通过逐步将一分一秒的教师采样员的产物图像与一分一秒的学生采样员($N/2美元)相匹配,以快速采样。在本文中,我们主张,这种以蒸馏为基础的加速方法可以进一步改进,特别是对几步采样者而言,特别是对于低步采样者,我们提议的\textbf{C}分样仪-基于\textbf{F}textbf{F}ture type f{D}stillation (CFD) 。我们不协调输出图像,而是用一个数据集独立分类器将教师的更精细的特征分布蒸馏到学生身上,使学生关注这些重要特征以提高性能。我们还引入了一个注重数据集的损失,以进一步优化模型。对CIFAR-10的实验显示我们的方法在达到高质量和快速采样方面的优势。代码在\/ github.com/zju-SWJ/RCFDDD}。</s>