计算机工程与应用 ›› 2019, Vol. 55 ›› Issue (3): 1-9.DOI: 10.3778/j.issn.1002-8331.1810-0284

• 热点与综述 • 上一篇    下一篇

变分自编码器模型综述

翟正利,梁振明,周  炜,孙  霞   

  1. 青岛理工大学  信息与控制工程学院,山东 青岛 266520
  • 出版日期:2019-02-01 发布日期:2019-01-24

Research Overview of Variational Auto-Encoders Models

ZHAI Zhengli, LIANG Zhenming, ZHOU Wei, SUN Xia   

  1. School of Information and Control Engineering, Qingdao University of Technology, Qingdao, Shandong 266520, China
  • Online:2019-02-01 Published:2019-01-24

摘要: 变分自编码器(VAE)作为深度隐空间生成模型的一种,近年来其表现性能取得了极大的成功,尤其是在图像生成方面。变分自编码器模型作为无监督式特征学习的重要工具之一,可以通过学习隐编码空间与数据生成空间的特征映射,进而在输出端重构生成输入数据。梳理了传统变分自编码器模型及其衍生变体模型的发展与研究现状,并就此做了总结和对比,最后分析了变分自编码器模型存在的问题与挑战,并就可能的发展趋势做了展望。

关键词: 深度隐空间生成模型, 无监督学习, 变分自编码器, 图像生成

Abstract: Variational Auto-Encoders(VAE) as one of deep latent space generative models have been immensely success on its performance in recent years, especially in image generation. VAEs models are important tools for unsupervised feature learning, which can learn a mapping from a latent encoding space to a data generative space and reconstruct the inputs to outputs. Firstly, this paper reviews the development and present research situation of the traditional variational auto-encoders and its variants, summarizes and compares the performance for all of them. Finally, the existing difficulties and challenges of VAEs are analyzed, and the possible development direction is prospected.

Key words: deep latent space generative models, unsupervised learning, Variational Auto-Encoders(VAEs), image generation