Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 41, Issue 10, Pages 2380-2394Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2018.2858819
Keywords
Face synthesis; unconstrained face recognition; 3D face model; generative adversarial networks
Funding
- China Scholarship Council (CSC) [201503170248]
- National Science Foundation of Chian [61672519]
- National University of Singapore [R-263-000-C08-133, MOE Tier-I R-263-000-C21-112, NUS IDS R-263-000-C67-646, ECRA R-263-000-C87-133]
Ask authors/readers for more resources
Synthesizing realistic profile faces is beneficial for more efficiently training deep pose-invariant models for large-scale unconstrained face recognition, by augmenting the number of samples with extreme poses and avoiding costly annotation work. However, learning from synthetic faces may not achieve the desired performance due to the discrepancy betwedistributions of the synthetic and real face images. To narrow this gap, we propose a Dual-Agent Generative Adversarial Network (DA-GAN) model, which can improve the realism of a face simulator's output using unlabeled real faces while preserving the identity information during the realism refinement. The dual agents are specially designed for distinguishing real versus fake and identities simultaneously. In particular, we employ an off-the-shelf 3D face model as a simulator to generate profile face images with varying poses. DA-GAN leverages a fully convolutional network as the generator to generate high-resolution images and an auto-encoder as the discriminator with the dual agents. Besides the novel architecture, we make several key modifications to the standard GAN to preserve pose, texture as well as identity, and stabilize the training process: (i) a pose perception loss; (ii) an identity perception loss; (iii) an adversarial loss with a boundary equilibrium regularization term. Experimental results show that DA-GAN not only achieves outstanding perceptual results but also significantly outperforms state-of-the-arts on the large-scale and challenging NIST IJB-A and CFP unconstrained face recognition benchmarks. In addition, the proposed DA-GAN is also a promising new approach for solving generic transfer learning problems more effectively. DA-GAN is the foundation of our winning entry to the NIST IJB-A face recognition competition in which we secured the 1st places on the tracks of verification and identification.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available