Score-matching and diffusion models have emerged as state-of-the-art generative models for both conditional and unconditional generation. Classifier-guided diffusion models are created by training a classifier on samples obtained from the forward-diffusion process (i.e., from data to noise). In this paper, we propose denoising-assisted (DA) classifiers wherein the diffusion classifier is trained using both noisy and denoised examples as simultaneous inputs to the model. We differentiate between denoising-assisted (DA) classifiers and noisy classifiers, which are diffusion classifiers that are only trained on noisy examples. Our experiments on Cifar10 and Imagenet show that DA-classifiers improve over noisy classifiers both quantitatively in terms of generalization to test data and qualitatively in terms of perceptually-aligned classifier-gradients and generative modeling metrics. Finally, we describe a semi-supervised framework for training diffusion classifiers and our experiments, that also include positive-unlabeled settings, demonstrate improved generalization of DA-classifiers over noisy classifiers.

翻译：评分匹配和扩散模型已成为条件生成和非条件生成领域的最先进生成模型。分类器引导的扩散模型通过在正向扩散过程（即从数据到噪声）中获得的样本上训练分类器而创建。本文提出去噪辅助（DA）分类器，其中扩散分类器的训练同时使用噪声样本和去噪样本作为模型的输入。我们将去噪辅助（DA）分类器与噪声分类器（仅使用噪声样本训练的扩散分类器）加以区分。在Cifar10和ImageNet上的实验表明，DA分类器在测试数据的泛化能力（定量指标）以及感知对齐的分类器梯度和生成建模指标（定性指标）上均优于噪声分类器。最后，我们描述了一种用于训练扩散分类器的半监督框架，实验（包括正-无标签设置）表明DA分类器比噪声分类器具有更好的泛化性能。