Skip to main navigation Skip to search Skip to main content

Re-Training StyleGAN-A First Step towards Building Large, Scalable Synthetic Facial Datasets

  • University of Galway
  • University of Antwerp

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

6 Citations (Scopus)

Abstract

StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper we recap the StyleGAN architecture and training methodology and present our experiences of retraining it on a number of alternative public datasets. Practical issues and challenges arising from the retraining process are discussed. Tests and validation results are presented and a comparative analysis of several different re-trained StyleGAN weightings is provided. The role of this tool in building large, scalable datasets of synthetic facial data is also discussed.

Original languageEnglish
Title of host publication2020 31st Irish Signals and Systems Conference, ISSC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728194189
DOIs
Publication statusPublished - Jun 2020
Event31st Irish Signals and Systems Conference, ISSC 2020 - Letterkenny, Ireland
Duration: 11 Jun 202012 Jun 2020

Publication series

Name2020 31st Irish Signals and Systems Conference, ISSC 2020

Conference

Conference31st Irish Signals and Systems Conference, ISSC 2020
Country/TerritoryIreland
CityLetterkenny
Period11/06/2012/06/20

Keywords

  • GANs
  • StyleGAN
  • face recognition
  • generative adversarial networks
  • sunthetic face data

Fingerprint

Dive into the research topics of 'Re-Training StyleGAN-A First Step towards Building Large, Scalable Synthetic Facial Datasets'. Together they form a unique fingerprint.

Cite this