Selective Sampling and Mixture Models in Generative Adversarial Networks

In this paper, we propose a multi-generator extension to the adversarial training framework, in which the objective of each generator is to represent a unique component of a target mixture distribution. In the training phase, the generators cooperate to represent, as a mixture, the target distribution while maintaining distinct manifolds. As opposed to traditional generative models, inference from a particular generator after training resembles selective sampling from a unique component in the target distribution. We demonstrate the feasibility of the proposed architecture both analytically and with basic Multi-Layer Perceptron (MLP) models trained on the MNIST dataset.

[1]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[4]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

[5]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[6]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[7]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[8]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[9]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.

[10]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[13]  Antonio Torralba,et al.  Generating Videos with Scene Dynamics , 2016, NIPS.

[14]  Abhinav Gupta,et al.  Generative Image Modeling Using Style and Structure Adversarial Networks , 2016, ECCV.

[15]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  Mykel J. Kochenderfer,et al.  Imitating driver behavior with generative adversarial networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[17]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[18]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

[19]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[20]  Chuan Li,et al.  Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks , 2016, ECCV.

[21]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[22]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[23]  Won-Ki Jeong,et al.  Compressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networks , 2017, ArXiv.

[24]  Raja Bala,et al.  Semi-supervised Conditional GANs , 2017, ArXiv.

[25]  Won-Ki Jeong,et al.  Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss , 2017, IEEE Transactions on Medical Imaging.

[26]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[27]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[28]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[29]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[30]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .