条件概率图产生式对抗网络  

Conditional Graphical Generative Adversarial Networks

作　　者：李崇轩 朱军[1] 张钹[1] LI Chong-Xuan;ZHU Jun;ZHANG Bo(Department of Computer Science and Technology,Tsinghua University,Beijing100084,China)

机构地区：[1]清华大学计算机科学与技术系,北京100084

出　　处：《软件学报》2020年第4期1002-1008,共7页Journal of Software

基　　金：国家自然科学基金(61620106010,61621136008);博士后创新人才拔尖计划。

摘　　要：产生式对抗网络(generative adversarial networks,简称GANs)可以生成逼真的图像,因此最近被广泛研究.值得注意的是,概率图生成对抗网络(graphical-GAN)将贝叶斯网络引入产生式对抗网络框架,以无监督的方式学习到数据的隐藏结构.提出了条件概率图生成对抗网络(conditional graphical-GAN),它可以在弱监督环境下,利用粗粒度监督信息来学习到更精细而复杂的结构.条件概率图生成对抗网络的推理和学习遵循与graphical-GAN类似的方法.提出了条件概率图生成对抗网络的两个实例.条件高斯混合模型(conditional Gaussian mixture GAN,简称cGMGAN)可以在给出粗粒度标签的情况下从混合数据中学习细粒度聚类.条件状态空间模型(conditional state space GAN,简称cSSGAN)可以在给定对象标签的情况下学习具有多个对象的视频的动态过程.Generative adversarial networks(GANs)have been promise on generating realistic images and hence have been studied widely.Notably,graphical generative adversarial networks(graphical-GAN)introduce Bayesian networks to the GAN framework to learn the underlying structures of data in an unsupervised manner.This study proposes a conditional version of graphical-GAN,which can leverage coarse side information to enhance the graphical-GAN and learn finer and more complex structures,in weakly-supervised learning settings.The inference and learning of conditional graphical-GAN follows a similar protocol to graphical-GAN.Two instances of conditional graphical-GAN are presented.The conditional Gaussian mixture GAN can learn fine clusters from mixture data given a coarse label.The conditional state space GAN can learn the dynamics of videos with multiple objects given the labels of the objects..

关 键 词：深度生成模型 产生式对抗网络 概率图模型 弱监督学习 条件模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]