Conditional Graphical Generative Adversarial Networks

被引：0
|
作者：
Li C.-X. [1 ]
Zhu J. [1 ]
Zhang B. [1 ]
机构：
[1] Department of Computer Science and Technology, Tsinghua University, Beijing
来源：
Ruan Jian Xue Bao/Journal of Software | 2020年 / 31卷 / 04期
基金：
中国国家自然科学基金;
关键词：
Conditional model; Deep generative model; Generative adversarial network; Graphical model; Weakly-supervised learning;
D O I：
10.13328/j.cnki.jos.005924
中图分类号：
学科分类号：
摘要：
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. © Copyright 2020, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：1002 / 1008
页数：6
相关论文
共 11 条
  • [1] Goodfellow I., Mirza M., Xu B., Farley D., Ozair S., Courville A., Bengio Y., Generative adversarial nets, Advances in Neural Information Processing Systems, pp. 2672-2680, (2014)
  • [2] Radford A., Metz L., Chintala S., Unsupervised representation learning with deep convolutional generative adversarial networks, Proc. of the Int'l Conf. on Learning Representations, (2015)
  • [3] Arjovsky M., Chintala S., Bottou L., Wasserstein GAN, Proc. of the Int'l Conf. on Machine Learning, pp. 214-223, (2015)
  • [4] Chen X., Duan Y., Houthooft R., Schulman J., Sutskever I., Abbeel P., InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets, Advances in Neural Information Processing Systems, pp. 2172-2180, (2016)
  • [5] Li C., Welling M., Zhu J., Zhang B., Graphical generative adversarial networks, Advances in Neural Information Processing Systems, pp. 6073-6083, (2018)
  • [6] Minka T., Expectation propagation for approximate Bayesian inference, Proc. of the 17th Conf. on Uncertainty in Artificial Intelligence, pp. 362-369, (2001)
  • [7] Jordan M., Ghahramani Z., Jaakkola T., Saul L., An introduction to variational methods for graphical models, Machine Learning, 37, 2, pp. 183-233, (1999)
  • [8] Stuhlmuller A., Taylor J., Goodman N., Learning stochastic inverses, Advances in Neural Information Processing Systems, pp. 3048-3056, (2013)
  • [9] Donahue J., Henbuhl P., Darrell T., Adversarial feature learning, Proc. of the Int'l Conf. on Learning Representations, (2017)
  • [10] Dumoulin V., Belghazi I., Poole B., Lamb A., Arjovsky M., Mastropietro O., Courville A., Adversarially learned inference, Proc. of the Int'l Conf. on Learning Representations, (2017)
12