A progressive growing of conditional generative adversarial networks model

Progressive growing of generative adversarial networks (PGGAN) is an adversarial network model that can generate high-resolution images.However, when the categories of samples are unbalanced, or the categories of samples are too similar or too dissimilar, it is prone to produce mode collapse, result...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui MA, Ruiqin WANG, Shuai YANG
Format: Article
Language:zho
Published: Beijing Xintong Media Co., Ltd 2023-06-01
Series:Dianxin kexue
Subjects:
Online Access:http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023134/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841530838464856064
author Hui MA
Ruiqin WANG
Shuai YANG
author_facet Hui MA
Ruiqin WANG
Shuai YANG
author_sort Hui MA
collection DOAJ
description Progressive growing of generative adversarial networks (PGGAN) is an adversarial network model that can generate high-resolution images.However, when the categories of samples are unbalanced, or the categories of samples are too similar or too dissimilar, it is prone to produce mode collapse, resulting in poor image generation effect.A progressive growing of conditional generative adversarial networks (PGCGAN) model was proposed.The idea of conditional generative adversarial networks (CGAN) was introduced into PGGAN.Using category information as condition, PGGAN was improved in two aspects of network structure and mini-batch standard deviation, and the phenomenon of model collapse in the process of image generation was alleviated.In the experiments on the three data sets, compared with PGGAN, PGCGAN has a greater degree of improvement in inception score and Fréchet inception distance, two evaluation indicators for image generation, and the generated images have higher diversity and authenticity; and PGCGAN multiple unrelated datasets can be trained simultaneously without crashing, and high-quality images can be produced in datasets with imbalanced categories or data that are too similar and dissimilar.
format Article
id doaj-art-8007af84f24a47ff86bb2a816cd899b6
institution Kabale University
issn 1000-0801
language zho
publishDate 2023-06-01
publisher Beijing Xintong Media Co., Ltd
record_format Article
series Dianxin kexue
spelling doaj-art-8007af84f24a47ff86bb2a816cd899b62025-01-15T02:58:34ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-06-013910511359565935A progressive growing of conditional generative adversarial networks modelHui MARuiqin WANGShuai YANGProgressive growing of generative adversarial networks (PGGAN) is an adversarial network model that can generate high-resolution images.However, when the categories of samples are unbalanced, or the categories of samples are too similar or too dissimilar, it is prone to produce mode collapse, resulting in poor image generation effect.A progressive growing of conditional generative adversarial networks (PGCGAN) model was proposed.The idea of conditional generative adversarial networks (CGAN) was introduced into PGGAN.Using category information as condition, PGGAN was improved in two aspects of network structure and mini-batch standard deviation, and the phenomenon of model collapse in the process of image generation was alleviated.In the experiments on the three data sets, compared with PGGAN, PGCGAN has a greater degree of improvement in inception score and Fréchet inception distance, two evaluation indicators for image generation, and the generated images have higher diversity and authenticity; and PGCGAN multiple unrelated datasets can be trained simultaneously without crashing, and high-quality images can be produced in datasets with imbalanced categories or data that are too similar and dissimilar.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023134/generative adversarial networkprogressive growing of conditional GANmini-batch standard deviationimage generation
spellingShingle Hui MA
Ruiqin WANG
Shuai YANG
A progressive growing of conditional generative adversarial networks model
Dianxin kexue
generative adversarial network
progressive growing of conditional GAN
mini-batch standard deviation
image generation
title A progressive growing of conditional generative adversarial networks model
title_full A progressive growing of conditional generative adversarial networks model
title_fullStr A progressive growing of conditional generative adversarial networks model
title_full_unstemmed A progressive growing of conditional generative adversarial networks model
title_short A progressive growing of conditional generative adversarial networks model
title_sort progressive growing of conditional generative adversarial networks model
topic generative adversarial network
progressive growing of conditional GAN
mini-batch standard deviation
image generation
url http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023134/
work_keys_str_mv AT huima aprogressivegrowingofconditionalgenerativeadversarialnetworksmodel
AT ruiqinwang aprogressivegrowingofconditionalgenerativeadversarialnetworksmodel
AT shuaiyang aprogressivegrowingofconditionalgenerativeadversarialnetworksmodel
AT huima progressivegrowingofconditionalgenerativeadversarialnetworksmodel
AT ruiqinwang progressivegrowingofconditionalgenerativeadversarialnetworksmodel
AT shuaiyang progressivegrowingofconditionalgenerativeadversarialnetworksmodel