Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

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 <PRE_TAG>score training</POST_TAG>, 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 <PRE_TAG>score</POST_TAG> at the optimal <PRE_TAG>discriminator</POST_TAG>, which implies that the discriminator helps better <PRE_TAG>score estimation</POST_TAG> 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.