Cover Image

LiWGAN: A light method to improve the performance of generative adversarial network

Generative adversarial networks (GANs) gained tremendous growth due to the potency and efficiency in producing realistic samples. This study proposes a light-weight GAN (LiWGAN) to learn non-image synthesis with minimum computational time for less power computing. Hence, the LiWGAN method enhanced a...

Full description

Saved in:
Bibliographic Details
Main Authors: Mashudi, Nurul Amirah, Ahmad, Norulhusna, Mohd. Noor, Norliza
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2022
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/104422/1/NorlizaMohdNoor2022_LiWGANALightMethodtoImprovethePerformance.pdf
http://eprints.utm.my/104422/
http://dx.doi.org/10.1109/ACCESS.2022.3203065
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.104422
record_format eprints
spelling my.utm.1044222024-02-04T09:58:33Z http://eprints.utm.my/104422/ LiWGAN: A light method to improve the performance of generative adversarial network Mashudi, Nurul Amirah Ahmad, Norulhusna Mohd. Noor, Norliza T Technology (General) Generative adversarial networks (GANs) gained tremendous growth due to the potency and efficiency in producing realistic samples. This study proposes a light-weight GAN (LiWGAN) to learn non-image synthesis with minimum computational time for less power computing. Hence, the LiWGAN method enhanced a new skip-layer channel-wise excitation module (SLE) and a self-supervised discriminator design for non-synthesis performance using the facemask dataset. Facemask is one of the preventative strategies pioneered by the current COVID-19 pandemic. LiWGAN manipulates a non-image synthesis of facemasks that could be beneficial for some researchers to identify an individual using lower power devices, occlusion challenges for face recognition, and alleviate the accuracy challenges due to limited datasets. The study evaluates the performance of the processing time in terms of batch sizes and image resolutions using the facemask dataset. The Fréchet inception distance (FID) was also measured on the facemask images to evaluate the quality of the augmented image using LiWGAN. The findings for 3000 generated images showed a nearly similar FID score at 220.43 with significantly less processing time per iteration at 1.03s than StyleGAN at 219.97 FID score. One experiment was conducted using the CelebA dataset to compare with GL-GAN and DRAGAN, proving LiWGAN is appropriate for other datasets. The outcomes found LiWGAN performed better than GL-GAN and DRAGAN at 91.31 FID score with 3.50s processing time per iteration. Therefore, LiWGAN could aim to enhance the FID score to be near zero in the future with less processing time by using different datasets. Institute of Electrical and Electronics Engineers Inc. 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/104422/1/NorlizaMohdNoor2022_LiWGANALightMethodtoImprovethePerformance.pdf Mashudi, Nurul Amirah and Ahmad, Norulhusna and Mohd. Noor, Norliza (2022) LiWGAN: A light method to improve the performance of generative adversarial network. IEEE Access, 10 (NA). pp. 93155-93167. ISSN 2169-3536 http://dx.doi.org/10.1109/ACCESS.2022.3203065 DOI : 10.1109/ACCESS.2022.3203065
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Mashudi, Nurul Amirah
Ahmad, Norulhusna
Mohd. Noor, Norliza
LiWGAN: A light method to improve the performance of generative adversarial network
description Generative adversarial networks (GANs) gained tremendous growth due to the potency and efficiency in producing realistic samples. This study proposes a light-weight GAN (LiWGAN) to learn non-image synthesis with minimum computational time for less power computing. Hence, the LiWGAN method enhanced a new skip-layer channel-wise excitation module (SLE) and a self-supervised discriminator design for non-synthesis performance using the facemask dataset. Facemask is one of the preventative strategies pioneered by the current COVID-19 pandemic. LiWGAN manipulates a non-image synthesis of facemasks that could be beneficial for some researchers to identify an individual using lower power devices, occlusion challenges for face recognition, and alleviate the accuracy challenges due to limited datasets. The study evaluates the performance of the processing time in terms of batch sizes and image resolutions using the facemask dataset. The Fréchet inception distance (FID) was also measured on the facemask images to evaluate the quality of the augmented image using LiWGAN. The findings for 3000 generated images showed a nearly similar FID score at 220.43 with significantly less processing time per iteration at 1.03s than StyleGAN at 219.97 FID score. One experiment was conducted using the CelebA dataset to compare with GL-GAN and DRAGAN, proving LiWGAN is appropriate for other datasets. The outcomes found LiWGAN performed better than GL-GAN and DRAGAN at 91.31 FID score with 3.50s processing time per iteration. Therefore, LiWGAN could aim to enhance the FID score to be near zero in the future with less processing time by using different datasets.
format Article
author Mashudi, Nurul Amirah
Ahmad, Norulhusna
Mohd. Noor, Norliza
author_facet Mashudi, Nurul Amirah
Ahmad, Norulhusna
Mohd. Noor, Norliza
author_sort Mashudi, Nurul Amirah
title LiWGAN: A light method to improve the performance of generative adversarial network
title_short LiWGAN: A light method to improve the performance of generative adversarial network
title_full LiWGAN: A light method to improve the performance of generative adversarial network
title_fullStr LiWGAN: A light method to improve the performance of generative adversarial network
title_full_unstemmed LiWGAN: A light method to improve the performance of generative adversarial network
title_sort liwgan: a light method to improve the performance of generative adversarial network
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2022
url http://eprints.utm.my/104422/1/NorlizaMohdNoor2022_LiWGANALightMethodtoImprovethePerformance.pdf
http://eprints.utm.my/104422/
http://dx.doi.org/10.1109/ACCESS.2022.3203065
_version_ 1792147738347962368
score 13.211869

Similar Items