The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or not. Unlike GANs, our approach does not require joint training of score and discriminator networks. Instead, we train the discriminator after score training, making discriminator training stable and fast to converge. In sample generation, we add an auxiliary term to the pre-trained score to deceive the discriminator. This term corrects the model score to the data score at the optimal discriminator, which implies that the discriminator helps better score estimation in a complementary way. Using our algorithm, we achive state-of-the-art results on ImageNet 256x256 with FID 1.83 and recall 0.64, similar to the validation data's FID (1.68) and recall (0.66). We release the code at https://github.com/alsdudrla10/DG.

翻译：本文提出一种名为“判别器引导”的方法，旨在改善预训练扩散模型的样本生成质量。该方法引入判别器，对去噪样本路径是否真实提供显式监督。与生成对抗网络不同，我们的方法无需联合训练分数网络与判别器网络，而是在分数模型训练完成后单独训练判别器，使判别器训练稳定且快速收敛。在样本生成阶段，我们向预训练分数添加辅助项以欺骗判别器。该项在最优判别器处将模型分数修正为数据分数，表明判别器能以互补方式辅助更优的分数估计。采用本算法，我们在ImageNet 256×256数据集上达到最优结果，FID为1.83，召回率为0.64，与验证数据的FID（1.68）和召回率（0.66）相近。代码已开源至https://github.com/alsdudrla10/DG。