University of Hertfordshire

From the same journal

By the same authors

Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy

Research output: Contribution to journalArticle

Standard

Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy. / Sáez-Trigueros, Daniel; Meng, Li; Hartnett, Margaret.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018.

Research output: Contribution to journalArticle

Harvard

APA

Sáez-Trigueros, D., Meng, L., & Hartnett, M. (2018). Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy. Manuscript submitted for publication.

Vancouver

Author

Bibtex

@article{ef265acbd4924170839065739adc9cd4,
title = "Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy",
abstract = "In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete identity labels to an identity latent space that follows a simple prior distribution, and training a GAN conditioned on samples from that distribution. Our proposed GAN allows us to augment face datasets by generating both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with augmented datasets can indeed increase the accuracy of face recognition models as compared with models trained with real images alone.",
author = "Daniel S{\'a}ez-Trigueros and Li Meng and Margaret Hartnett",
year = "2018",
language = "English",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",

}

RIS

TY - JOUR

T1 - Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy

AU - Sáez-Trigueros, Daniel

AU - Meng, Li

AU - Hartnett, Margaret

PY - 2018

Y1 - 2018

N2 - In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete identity labels to an identity latent space that follows a simple prior distribution, and training a GAN conditioned on samples from that distribution. Our proposed GAN allows us to augment face datasets by generating both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with augmented datasets can indeed increase the accuracy of face recognition models as compared with models trained with real images alone.

AB - In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete identity labels to an identity latent space that follows a simple prior distribution, and training a GAN conditioned on samples from that distribution. Our proposed GAN allows us to augment face datasets by generating both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with augmented datasets can indeed increase the accuracy of face recognition models as compared with models trained with real images alone.

UR - https://arxiv.org/abs/1811.00112

M3 - Article

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

ER -