Deep learning shows great potential in generation tasks thanks to deep latent representation. Generative models are classes of models that can generate observations randomly with respect to certain implied parameters. Recently, the diffusion Model becomes a raising class of generative models by virtue of its power-generating ability. Nowadays, great achievements have been reached. More applications except for computer vision, speech generation, bioinformatics, and natural language processing are to be explored in this field. However, the diffusion model has its natural drawback of a slow generation process, leading to many enhanced works. This survey makes a summary of the field of the diffusion model. We firstly state the main problem with two landmark works - DDPM and DSM. Then, we present a diverse range of advanced techniques to speed up the diffusion models - training schedule, training-free sampling, mixed-modeling, and score & diffusion unification. Regarding existing models, we also provide a benchmark of FID score, IS, and NLL according to specific NFE. Moreover, applications with diffusion models are introduced including computer vision, sequence modeling, audio, and AI for science. Finally, there is a summarization of this field together with limitations & further directions.
翻译:深层学习显示,由于深层潜在代表性,在生成任务方面具有巨大的潜力。 生成模型是能够随机对某些隐含参数进行观测的模型类别。 最近, 扩散模型因其发电能力而成为基因模型的一个提高级。 如今, 已经取得了巨大的成就。 将在这一领域探索更多的应用, 除了计算机视觉、 语音生成、 生物信息学和自然语言处理之外。 但是, 扩散模型有其缓慢生成过程的自然缺陷, 导致许多强化工程。 本次调查总结了传播模型的领域。 我们首先说明了两个里程碑式工程---- DDPM 和 DSM 的主要问题。 然后, 我们展示了各种先进技术, 以加速推广模型---- 培训时间表、 无培训抽样、 混合建模和得分和传播统一。 关于现有的模型, 我们还根据具体的NFEFE, 提供了一个FID评分、 IS 和 NLLL的基准。 此外, 推广模型的应用包括计算机视觉、 序列建模、 音频 和 AI 科学 。 最后, 将这个领域与进一步的限制和方向一起进行总结。