Diffusion Probabilistic Models (DPMs) have demonstrated substantial promise in image generation tasks but heavily rely on the availability of large amounts of training data. Previous works, like GANs, have tackled the limited data problem by transferring pre-trained models learned with sufficient data. However, those methods are hard to be utilized in DPMs since the distinct differences between DPM-based and GAN-based methods, showing in the unique iterative denoising process integral and the need for many timesteps with no-targeted noise in DPMs. In this paper, we propose a novel DPMs-based transfer learning method, TAN, to address the limited data problem. It includes two strategies: similarity-guided training, which boosts transfer with a classifier, and adversarial noise selection which adaptive chooses targeted noise based on the input image. Extensive experiments in the context of few-shot image generation tasks demonstrate that our method is not only efficient but also excels in terms of image quality and diversity when compared to existing GAN-based and DDPM-based methods.

翻译：扩散概率模型（DPMs）在图像生成任务中展现出巨大潜力，但其性能高度依赖于大量训练数据的可用性。以往的研究，如生成对抗网络（GANs），通过迁移在充足数据上预训练的模型来应对数据有限问题。然而，这些方法难以直接应用于DPMs，因为基于DPM和基于GAN的方法存在显著差异，具体体现在DPMs特有的迭代去噪过程、需要大量时间步以及使用无目标噪声等方面。本文提出了一种新颖的基于DPMs的迁移学习方法TAN，以解决数据有限问题。该方法包含两种策略：通过分类器促进迁移的相似性引导训练，以及基于输入图像自适应选择目标噪声的对抗性噪声选择。在少样本图像生成任务的广泛实验中，我们的方法不仅效率高，而且在图像质量和多样性方面优于现有的基于GAN和基于DDPM的方法。