GRB-Sty: Redesign of Generative Residual Block for StyleGAN

We have previously published a paper introducing a novel module, the Generative Residual Block (GRB), which successfully enhances GAN performance. However, the experiments in the earlier paper were conducted on baseline models using spectral normalization, a technique seldom used today. To address t...

Full description

Saved in:
Bibliographic Details
Main Authors: Seung Park, Yong-Goo Shin
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:ICT Express
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405959525000232
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849338309076058112
author Seung Park
Yong-Goo Shin
author_facet Seung Park
Yong-Goo Shin
author_sort Seung Park
collection DOAJ
description We have previously published a paper introducing a novel module, the Generative Residual Block (GRB), which successfully enhances GAN performance. However, the experiments in the earlier paper were conducted on baseline models using spectral normalization, a technique seldom used today. To address this problem, we investigate the effectiveness of GRB on contemporary StyleGAN-based models. This paper introduces an enhanced version of GRB, termed GRB-Sty, which consistently boosts the performance of StyleGAN-based models and demonstrates versatility across various aspects. The significant performance enhancements observed in extensive experiments on multiple benchmark datasets highlight the compatibility of GRB-Sty with state-of-the-art methods.
format Article
id doaj-art-bc455c927bd54d3ebba1b2ab27c75552
institution Kabale University
issn 2405-9595
language English
publishDate 2025-04-01
publisher Elsevier
record_format Article
series ICT Express
spelling doaj-art-bc455c927bd54d3ebba1b2ab27c755522025-08-20T03:44:27ZengElsevierICT Express2405-95952025-04-0111222322710.1016/j.icte.2025.02.007GRB-Sty: Redesign of Generative Residual Block for StyleGANSeung Park0Yong-Goo Shin1Biomedical Engineering, Chungbuk National University Hospital, 776, Seowon-gu, Cheongju-si, Chungcheongbuk-do, Republic of KoreaDepartment of Electronics and Information Engineering, Korea University, 2511, Sejong-ro, Jochiwon-eup, Sejong-si, 30019, Republic of Korea; Corresponding author.We have previously published a paper introducing a novel module, the Generative Residual Block (GRB), which successfully enhances GAN performance. However, the experiments in the earlier paper were conducted on baseline models using spectral normalization, a technique seldom used today. To address this problem, we investigate the effectiveness of GRB on contemporary StyleGAN-based models. This paper introduces an enhanced version of GRB, termed GRB-Sty, which consistently boosts the performance of StyleGAN-based models and demonstrates versatility across various aspects. The significant performance enhancements observed in extensive experiments on multiple benchmark datasets highlight the compatibility of GRB-Sty with state-of-the-art methods.http://www.sciencedirect.com/science/article/pii/S2405959525000232Generative adversarial networksGenerative residual blockSide-residual pathStyleGAN
spellingShingle Seung Park
Yong-Goo Shin
GRB-Sty: Redesign of Generative Residual Block for StyleGAN
ICT Express
Generative adversarial networks
Generative residual block
Side-residual path
StyleGAN
title GRB-Sty: Redesign of Generative Residual Block for StyleGAN
title_full GRB-Sty: Redesign of Generative Residual Block for StyleGAN
title_fullStr GRB-Sty: Redesign of Generative Residual Block for StyleGAN
title_full_unstemmed GRB-Sty: Redesign of Generative Residual Block for StyleGAN
title_short GRB-Sty: Redesign of Generative Residual Block for StyleGAN
title_sort grb sty redesign of generative residual block for stylegan
topic Generative adversarial networks
Generative residual block
Side-residual path
StyleGAN
url http://www.sciencedirect.com/science/article/pii/S2405959525000232
work_keys_str_mv AT seungpark grbstyredesignofgenerativeresidualblockforstylegan
AT yonggooshin grbstyredesignofgenerativeresidualblockforstylegan