|
Title
|
|
|
|
Re-Training StyleGAN : a first step towards building large, scalable synthetic facial datasets
|
|
|
Author
|
|
|
|
|
|
|
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. |
|
|
|
Language
|
|
|
|
English
|
|
|
Source (journal)
|
|
|
|
Signals and Systems Conference (ISSC), Irish
|
|
|
Source (book)
|
|
|
|
31st Irish Signals and Systems Conference (ISSC), JUN 11-12, 2020, Letterkenny, Ireland
|
|
|
Publication
|
|
|
|
New york
:
Ieee
,
2020
|
|
|
ISBN
|
|
|
|
978-1-7281-9418-9
978-1-7281-9419-6
|
|
|
DOI
|
|
|
|
10.1109/ISSC49989.2020.9180189
|
|
|
Volume/pages
|
|
|
|
(2020)
, p. 267-272
|
|
|
ISI
|
|
|
|
000656045900045
|
|
|
Full text (Publisher's DOI)
|
|
|
|
|
|
|
Full text (open access)
|
|
|
|
|
|
|
Full text (publisher's version - intranet only)
|
|
|
|
|
|