Skip to main content

VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person

Publication ,  Journal Article
Pang, M; Wang, B; Cheung, YM; Chen, Y; Wen, B
Published in: IEEE Transactions on Information Forensics and Security
January 1, 2021

Single sample per person (SSPP) face recognition with a ${c}$ ontaminated biometric ${e}$ nrolment database (SSPP-ce FR) is an emerging practical FR problem, where the SSPP in the enrolment database is no longer standard but contaminated by nuisance facial variations such as expression, lighting, pose, and disguise. In this case, the conventional SSPP FR methods, including the patch-based and generic learning methods, will suffer from serious performance degradation. Few recent methods were proposed to tackle SSPP-ce FR by either performing prototype learning on the contaminated enrolment database or learning discriminative representations that are robust against variation. Despite that, most of these approaches can only handle a specified single variation, e.g., pose, but cannot be extended to multiple variations. To address these two limitations, we propose a novel Variation Disentangling Generative Adversarial Network (VD-GAN) to jointly perform prototype learning and representation learning in a unified framework. The proposed VD-GAN consists of an encoder-decoder structural generator and a multi-task discriminator to handle universal variations including single, multiple, and even mixed variations in practice. The generator and discriminator play an adversarial game such that the generator learns a discriminative identity representation and generates an identity-preserved prototype for each face image, while the discriminator aims to predict face identity label, distinguish real vs. fake prototype, and disentangle target variations from the learned representations. Qualitative and quantitative evaluations on various real-world face datasets containing single/multiple and mixed variations demonstrate the effectiveness of VD-GAN.

Duke Scholars

Published In

IEEE Transactions on Information Forensics and Security

DOI

EISSN

1556-6021

ISSN

1556-6013

Publication Date

January 1, 2021

Volume

16

Start / End Page

2246 / 2259

Related Subject Headings

  • Strategic, Defence & Security Studies
  • 46 Information and computing sciences
  • 40 Engineering
  • 09 Engineering
  • 08 Information and Computing Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Pang, M., Wang, B., Cheung, Y. M., Chen, Y., & Wen, B. (2021). VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person. IEEE Transactions on Information Forensics and Security, 16, 2246–2259. https://doi.org/10.1109/TIFS.2021.3050055
Pang, M., B. Wang, Y. M. Cheung, Y. Chen, and B. Wen. “VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person.” IEEE Transactions on Information Forensics and Security 16 (January 1, 2021): 2246–59. https://doi.org/10.1109/TIFS.2021.3050055.
Pang M, Wang B, Cheung YM, Chen Y, Wen B. VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person. IEEE Transactions on Information Forensics and Security. 2021 Jan 1;16:2246–59.
Pang, M., et al. “VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person.” IEEE Transactions on Information Forensics and Security, vol. 16, Jan. 2021, pp. 2246–59. Scopus, doi:10.1109/TIFS.2021.3050055.
Pang M, Wang B, Cheung YM, Chen Y, Wen B. VD-GAN: A Unified Framework for Joint Prototype and Representation Learning from Contaminated Single Sample per Person. IEEE Transactions on Information Forensics and Security. 2021 Jan 1;16:2246–2259.

Published In

IEEE Transactions on Information Forensics and Security

DOI

EISSN

1556-6021

ISSN

1556-6013

Publication Date

January 1, 2021

Volume

16

Start / End Page

2246 / 2259

Related Subject Headings

  • Strategic, Defence & Security Studies
  • 46 Information and computing sciences
  • 40 Engineering
  • 09 Engineering
  • 08 Information and Computing Sciences