Spotlight
Dual Variational Generation for Low Shot Heterogeneous Face Recognition
Chaoyou Fu · Xiang Wu · Yibo Hu · Huaibo Huang · Ran He

Tue Dec 10th 04:45 -- 04:50 PM @ West Exhibition Hall C + B3

Heterogeneous Face Recognition (HFR) is a challenging issue because of the large domain discrepancy and a lack of heterogeneous data. This paper considers HFR as a dual generation problem, and proposes a novel Dual Variational Generation (DVG) framework. It generates large-scale new paired heterogeneous images with the same identity from noise, for the sake of reducing the domain gap of HFR. Specifically, we first introduce a dual variational autoencoder to represent a joint distribution of paired heterogeneous images. Then, in order to ensure the identity consistency of the generated paired heterogeneous images, we impose a distribution alignment in the latent space and a pairwise identity preserving in the image space. Moreover, the HFR network reduces the domain discrepancy by constraining the pairwise feature distances between the generated paired heterogeneous images. Extensive experiments on four HFR databases show that our method can significantly improve state-of-the-art results. When using the generated paired images for training, our method gains more than 18\% True Positive Rate improvements over the baseline model when False Positive Rate is at $10^{-5}$.

Author Information

Chaoyou Fu (Institute of Automation, Chinese Academy of Sciences)
Xiang Wu (Institue of Automation, Chinese Academy of Science)
Yibo Hu (Institute of Automation, Chinese Academy of Sciences)
Huaibo Huang (Institute of Automation, Chinese Academy of Science)
Ran He (NLPR, CASIA)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors