Persistent Homology Based Generative Adversarial Network

Jinri Bao, Jinri Bao, Zicong Wang, Zicong Wang, Junli Wang, Junli Wang, Chungang Yan, Chungang Yan

2023

Abstract

In recent years, image generation has become one of the most popular research areas in the field of computer vision. Significant progress has been made in image generation based on generative adversarial network (GAN). However, the existing generative models fail to capture enough global structural information, which makes it difficult to coordinate the global structural features and local detail features during image generation. This paper proposes the Persistent Homology based Generative Adversarial Network (PHGAN). A topological feature transformation algorithm is designed based on the persistent homology method and then the topological features are integrated into the discriminator of GAN through the fully connected layer module and the self-attention module, so that the PHGAN has an excellent ability to capture global structural information and improves the generation performance of the model. We conduct an experimental evaluation of the PHGAN on the CIFAR10 dataset and the STL10 dataset, and compare it with several classic generative adversarial network models. The better results achieved by our proposed PHGAN show that the model has better image generation ability.

Paper Citation

in Harvard Style

Bao J., Wang Z., Wang J. and Yan C. (2023). Persistent Homology Based Generative Adversarial Network. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 196-203. DOI: 10.5220/0011648200003417

in Bibtex Style

@conference{visapp23,
author={Jinri Bao and Zicong Wang and Junli Wang and Chungang Yan},
title={Persistent Homology Based Generative Adversarial Network},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={196-203},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011648200003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Persistent Homology Based Generative Adversarial Network
SN - 978-989-758-634-7
AU - Bao J.
AU - Wang Z.
AU - Wang J.
AU - Yan C.
PY - 2023
SP - 196
EP - 203
DO - 10.5220/0011648200003417
PB - SciTePress