@inproceedings{1e190feb3d124df88e3ca6937d422525,
title = "Re-Training StyleGAN-A First Step towards Building Large, Scalable Synthetic Facial Datasets",
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.",
keywords = "GANs, StyleGAN, face recognition, generative adversarial networks, sunthetic face data",
author = "Viktor Varkarakis and Shabab Bazrafkan and Peter Corcoran",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 31st Irish Signals and Systems Conference, ISSC 2020 ; Conference date: 11-06-2020 Through 12-06-2020",
year = "2020",
month = jun,
doi = "10.13025/18638",
language = "English",
series = "2020 31st Irish Signals and Systems Conference, ISSC 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2020 31st Irish Signals and Systems Conference, ISSC 2020",
}