Diffusion models are a class of deep generative models that have shown impressive results on various tasks with dense theoretical founding. Although diffusion models have achieved more impressive quality and diversity of sample synthesis than other state-of-the-art models, they still suffer from costly sampling procedures and sub-optimal likelihood estimation. Recent studies have shown great enthusiasm for improving the performance of the diffusion model. In this article, we present the first comprehensive review of existing variants of diffusion models. Specifically, we provide the first taxonomy of diffusion models and categorize them into three types: sampling-acceleration enhancement, likelihood-maximization enhancement, and data-generalization enhancement. We also introduce the other five generative models (i.e., variational autoencoders, generative adversarial networks, normalizing flow, autoregressive models, and energy-based models) in detail and clarify the connections between diffusion models and these generative models. Then we thoroughly investigate the applications of diffusion models, including computer vision, natural language processing, waveform signal processing, multi-modal modeling, molecular graph generation, time series modeling, and adversarial purification. Furthermore, we propose new perspectives pertaining to the development of this generative model.
翻译:扩散模型是一种深层次的基因化模型,在理论基础密集的情况下,在各种任务上取得了令人印象深刻的成果。虽然传播模型比其他最先进的模型在样本合成方面的质量更高,而且多样性更大,但是它们仍然受到昂贵的取样程序和次优估计的损害。最近的研究显示,它们非常热衷于改进扩散模型的性能。在本条中,我们首次全面审查了传播模型的现有变异模型。具体地说,我们提供了传播模型的第一批分类,并将其分为三类:抽样加速增强、概率最大化增强和数据普及增强。我们还引进了其他五种基因化模型(即变异自动化模型、基因化对抗网络、正常化流动、自动递减模型和能源模型),详细并澄清了传播模型与这些变异模型之间的联系。然后,我们透彻地研究了传播模型的应用,包括计算机视觉、自然语言处理、波形信号处理、多模式建模、分子图生成、时间序列建模和对抗性净化等。此外,我们提出了与基因净化有关的新模型发展。