论文标题
在基于得分的扩散模型中使用歧视器指导来完善生成过程
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
论文作者
论文摘要
所提出的方法，即鉴别器指导，旨在改善预训练扩散模型的样本生成。该方法介绍了一个歧视者，该歧视者对降级样本路径进行明确监督，无论它是否现实。与甘斯不同，我们的方法不需要分数和歧视者网络的联合培训。取而代之的是，我们在得分训练后训练歧视者，从而使歧视者训练稳定并迅速融合。在样本生成中，我们在预训练的分数中添加了辅助术语，以欺骗歧视者。该术语将模型得分纠正为最佳歧视者的数据分数，这意味着歧视者以互补的方式有助于更好的分数估计。使用我们的算法，我们在ImageNet 256x256上获得了最新的结果，其FID 1.83和召回0.64，类似于验证数据的FID（1.68）和召回（0.66）。我们在https://github.com/alsdudrla10/dg上发布代码。
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.
