Diffusion Models have demonstrated remarkable performance in image
generation. However, their demanding computational requirements for training
have prompted ongoing efforts to enhance the quality of generated images
through modifications in the sampling process. A recent approach, known as
Discriminator Guidance, seeks to bridge the gap between the model score and the
data score by incorporating an auxiliary term, derived from a discriminator
network. We show that despite significantly improving sample quality, this
technique has not resolved the persistent issue of Exposure Bias and we propose
SEDM-G++, which incorporates a modified sampling approach, combining
Discriminator Guidance and Epsilon Scaling. Our proposed approach outperforms
the current state-of-the-art, by achieving an FID score of 1.73 on the
unconditional CIFAR-10 dataset.

SEDM-G++ 结合鉴别器引导和 Epsilon 缩放的改进取样方法，解决了扩大偏差的持久问题，提高了生成图像的质量。

降低鉴别器引导扩散模型中的曝光偏差

Mitigating Exposure Bias in Discriminator Guided Diffusion Models

We introduce discriminator guidance in the setting of Autoregressive
Diffusion Models. The use of a discriminator to guide a diffusion process has
previously been used for continuous diffusion models, and in this work we
derive ways of using a discriminator together with a pretrained generative
model in the discrete case. First, we show that using an optimal discriminator
will correct the pretrained model and enable exact sampling from the underlying
data distribution. Second, to account for the realistic scenario of using a
sub-optimal discriminator, we derive a sequential Monte Carlo algorithm which
iteratively takes the predictions from the discrimiator into account during the
generation process. We test these approaches on the task of generating
molecular graphs and show how the discriminator improves the generative
performance over using only the pretrained model.

在 Autoregressive Diffusion Models 中引入鉴别器指导，结合预先训练的生成模型，在离散情况下使用最优鉴别器可以纠正预训练模型并从底层数据分布中精确采样；针对使用次优鉴别器的实际情况，我们提出了一种顺序蒙特卡罗算法，在生成过程中迭代地考虑鉴别器的预测。我们在生成分子图的任务上对这些方法进行了测试，展示了鉴别器如何提高生成性能，超过仅使用预先训练的模型。