CapsuleGAN: Generative Adversarial Capsule Network
Abstract
We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adversarial network (GAN) setting, while modeling image data. We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates the CapsNet margin loss, for training CapsuleGAN models. We show that CapsuleGAN outperforms convolutional-GAN at modeling image data distribution on MNIST and CIFAR-10 datasets, evaluated on the generative adversarial metric and at semi-supervised image classification.
Cite
@article{arxiv.1802.06167,
title = {CapsuleGAN: Generative Adversarial Capsule Network},
author = {Ayush Jaiswal and Wael AbdAlmageed and Yue Wu and Premkumar Natarajan},
journal= {arXiv preprint arXiv:1802.06167},
year = {2018}
}
Comments
To appear in Proceedings of ECCV Workshop on Brain Driven Computer Vision (BDCV) 2018