A prominent family of methods for learning data distributions relies on density ratio estimation (DRE), where a model is trained to $\textit{classify}$ between data samples and samples from some reference distribution. These techniques are successful in simple low-dimensional settings but fail to achieve good results on complex high-dimensional data, like images. A different family of methods for learning distributions is that of denoising diffusion models (DDMs), in which a model is trained to $\textit{denoise}$ data samples. These approaches achieve state-of-the-art results in image, video, and audio generation. In this work, we present $\textit{Classification Diffusion Models}$ (CDMs), a generative technique that adopts the denoising-based formalism of DDMs while making use of a classifier that predicts the amount of noise added to a clean signal, similarly to DRE methods. Our approach is based on the observation that an MSE-optimal denoiser for white Gaussian noise can be expressed in terms of the gradient of a cross-entropy-optimal classifier for predicting the noise level. As we illustrate, CDM achieves better denoising results compared to DDM, and leads to at least comparable FID in image generation. CDM is also capable of highly efficient one-step exact likelihood estimation, achieving state-of-the-art results among methods that use a single step. Code is available on the project's webpage in https://shaharYadin.github.io/CDM/ .

翻译：一类重要的数据分布学习方法依赖于密度比估计（DRE），即训练模型对数据样本与来自某种参考分布的样本进行$\textit{分类}$。这些技术在简单的低维场景中表现良好，但在处理图像等复杂高维数据时效果不佳。另一类分布学习方法是去噪扩散模型（DDM），其中模型被训练用于对数据样本进行$\textit{去噪}$。这类方法在图像、视频和音频生成中达到了最先进的性能。本文提出$\textit{分类扩散模型}$（CDM），这是一种生成技术，采用DDM的基于去噪的形式化方法，同时利用分类器预测添加到干净信号中的噪声量，类似于DRE方法。我们的方法基于以下观察：针对白高斯噪声的MSE最优去噪器可以用交叉熵最优分类器（用于预测噪声水平）的梯度表示。实验表明，CDM在去噪结果上优于DDM，并在图像生成中取得了至少与DDM相当的FID值。此外，CDM还能实现高效的单步精确似然估计，在单步方法中达到最先进的结果。代码可在项目网页https://shaharYadin.github.io/CDM/获取。