# CapsuleGAN: Generative Adversarial Capsule Network

Source: [CapsuleGAN: Generative Adversarial Capsule Network](<https://www.sota2.com/research/paper/68fa64e41e209131cea072b3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:13:58.604Z

Authors: Ayush Jaiswal, Wael AbdAlmageed, Yue Wu, Premkumar Natarajan

Published: 2018-02-17T01:04:53.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1802.06167>)

[PDF](<https://arxiv.org/pdf/1802.06167.pdf>)