Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks

In this paper, we propose Generative Adversarial Network (GAN) architectures that use Capsule Networks for image-synthesis. Based on the principal of positional-equivariance of features, Capsule Network's ability to encode spatial relationships between the features of the image helps it become...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-11
Main Authors: Upadhyay, Yash, Schrater, Paul
Format: Article
Language:English
Subjects:
Artificial neural networks
Generative adversarial networks
Neural networks
Synthesis
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose Generative Adversarial Network (GAN) architectures that use Capsule Networks for image-synthesis. Based on the principal of positional-equivariance of features, Capsule Network's ability to encode spatial relationships between the features of the image helps it become a more powerful critic in comparison to Convolutional Neural Networks (CNNs) used in current architectures for image synthesis. Our proposed GAN architectures learn the data manifold much faster and therefore, synthesize visually accurate images in significantly lesser number of training samples and training epochs in comparison to GANs and its variants that use CNNs. Apart from analyzing the quantitative results corresponding the images generated by different architectures, we also explore the reasons for the lower coverage and diversity explored by the GAN architectures that use CNN critics.
ISSN:2331-8422