CapsuleGAN: Generative Adversarial Capsule Network

Ayush Jaiswal, Wael AbdAlmageed, Yue Wu, Premkumar Natarajan

ECCVW 2018 pp. 526-535

doi:10.1007/978-3-030-11015-4_38 /eccvw/2018/jaiswal2018eccvw-capsulegan/

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 the MNIST dataset of handwritten digits, evaluated on the generative adversarial metric and at semi-supervised image classification.

PDF ECCVW Semantic Scholar

Cite

Text

Jaiswal et al. "CapsuleGAN: Generative Adversarial Capsule Network." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11015-4_38

Markdown

[Jaiswal et al. "CapsuleGAN: Generative Adversarial Capsule Network." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/jaiswal2018eccvw-capsulegan/) doi:10.1007/978-3-030-11015-4_38

BibTeX

@inproceedings{jaiswal2018eccvw-capsulegan,
  title     = {{CapsuleGAN: Generative Adversarial Capsule Network}},
  author    = {Jaiswal, Ayush and AbdAlmageed, Wael and Wu, Yue and Natarajan, Premkumar},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {526-535},
  doi       = {10.1007/978-3-030-11015-4_38},
  url       = {https://mlanthology.org/eccvw/2018/jaiswal2018eccvw-capsulegan/}
}