University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning

Hu, Cong, Feng, Zhen-Hua, Wu, Xiao-Jun and Kittler, Josef (2020) Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning IEEE Access, 8. pp. 130-159.

[img]
Preview
Text
09141259.pdf - Proof

Download (2MB) | Preview
[img]
Preview
Text
09141259.pdf - Version of Record
Available under License Creative Commons Attribution.

Download (1MB) | Preview

Abstract

To learn disentangled representations of facial images, we present a Dual Encoder-Decoder based Generative Adversarial Network (DED-GAN). In the proposed method, both the generator and discriminator are designed with deep encoder-decoder architectures as their backbones. To be more specific, the encoder-decoder structured generator is used to learn a pose disentangled face representation, and the encoder-decoder structured discriminator is tasked to perform real/fake classification, face reconstruction, determining identity and estimating face pose. We further improve the proposed network architecture by minimizing the additional pixel-wise loss defined by the Wasserstein distance at the output of the discriminator so that the adversarial framework can be better trained. Additionally, we consider face pose variation to be continuous, rather than discrete in existing literature, to inject richer pose information into our model. The pose estimation task is formulated as a regression problem, which helps to disentangle identity information from pose variations. The proposed network is evaluated on the tasks of pose-invariant face recognition (PIFR) and face synthesis across poses. An extensive quantitative and qualitative evaluation carried out on several controlled and in-the-wild benchmarking datasets demonstrates the superiority of the proposed DED-GAN method over the state-of-the-art approaches.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Computer Science
Authors :
NameEmailORCID
Hu, Cong
Feng, Zhen-Huaz.feng@surrey.ac.uk
Wu, Xiao-Jun
Kittler, JosefJ.Kittler@surrey.ac.uk
Date : 15 July 2020
DOI : 10.1109/ACCESS.2020.3009512
Copyright Disclaimer : This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
Uncontrolled Keywords : Disentangled representation learning; encoder-decoder; generative adversarial networks; face synthesis; pose invariant face recognition
Additional Information : Embargo OK Metadata OK No Further Action
Depositing User : James Marshall
Date Deposited : 16 Jul 2020 10:52
Last Modified : 23 Jul 2020 08:13
URI: http://epubs.surrey.ac.uk/id/eprint/858224

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800