Generating Synthetic Faces for Data Augmentation with StyleGAN2-ADA

Natália Meira, Mateus Silva, Andrea Gomes Campos Bianchi, Ricardo Oliveira

2023

Abstract

Generative deep learning models based on Autoencoders and Generative Adversarial Networks (GANs) have enabled increasingly realistic face-swapping tasks. The generation of representative synthetic datasets is an example of this application. These datasets need to encompass ethnic, racial, gender, and age range diversity so that deep learning models can avoid biases and discrimination against certain groups of individuals, reproducing implicit biases in poorly constructed datasets. In this work, we implement a StyleGAN2-ADA to generate representative synthetic data from the FFHQ dataset. This work consists of step 1 of a face-swap pipeline using synthetic facial data in videos to augment data in artificial intelligence model problems. We were able to generate synthetic facial data but found limitations due to the presence of artifacts in most images.

Paper Citation

in Harvard Style

Meira N., Silva M., Gomes Campos Bianchi A. and Oliveira R. (2023). Generating Synthetic Faces for Data Augmentation with StyleGAN2-ADA. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-648-4, SciTePress, pages 649-655. DOI: 10.5220/0011994600003467

in Bibtex Style

@conference{iceis23,
author={Natália Meira and Mateus Silva and Andrea Gomes Campos Bianchi and Ricardo Oliveira},
title={Generating Synthetic Faces for Data Augmentation with StyleGAN2-ADA},
booktitle={Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2023},
pages={649-655},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011994600003467},
isbn={978-989-758-648-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Generating Synthetic Faces for Data Augmentation with StyleGAN2-ADA
SN - 978-989-758-648-4
AU - Meira N.
AU - Silva M.
AU - Gomes Campos Bianchi A.
AU - Oliveira R.
PY - 2023
SP - 649
EP - 655
DO - 10.5220/0011994600003467
PB - SciTePress