DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition

by   Chaoyou Fu, et al.

Heterogeneous Face Recognition (HFR) refers to matching cross-domain faces, playing a crucial role in public security. Nevertheless, HFR is confronted with the challenges from large domain discrepancy and insufficient heterogeneous data. In this paper, we formulate HFR as a dual generation problem, and tackle it via a novel Dual Variational Generation (DVG-Face) framework. Specifically, a dual variational generator is elaborately designed to learn the joint distribution of paired heterogeneous images. However, the small-scale paired heterogeneous training data may limit the identity diversity of sampling. With this in mind, we propose to integrate abundant identity information of large-scale VIS images into the joint distribution. Furthermore, a pairwise identity preserving loss is imposed on the generated paired heterogeneous images to ensure their identity consistency. As a consequence, massive new diverse paired heterogeneous images with the same identity can be generated from noises. The identity consistency and diversity properties allow us to employ these generated images to train the HFR network via a contrastive learning mechanism, yielding both domain invariant and discriminative embedding features. Concretely, the generated paired heterogeneous images are regarded as positive pairs, and the images obtained from different samplings are considered as negative pairs. Our method achieves superior performances over state-of-the-art methods on seven databases belonging to five HFR tasks, including NIR-VIS, Sketch-Photo, Profile-Frontal Photo, Thermal-VIS, and ID-Camera. The related code will be released at https://github.com/BradyFU.


page 2

page 4

page 7

page 8

page 10

page 12


Dual Variational Generation for Low-Shot Heterogeneous Face Recognition

Heterogeneous Face Recognition (HFR) is a challenging issue because of t...

Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement

Heterogeneous Face Recognition (HFR) aims to match faces across differen...

Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

Heterogeneous face recognition (HFR) refers to matching face images acqu...

Disentangled Variational Representation for Heterogeneous Face Recognition

Visible (VIS) to near infrared (NIR) face matching is a challenging prob...

Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning

Face anti-spoofing (FAS) plays a vital role in preventing face recogniti...

Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination

In Heterogeneous Face Recognition (HFR), the objective is to match faces...

Decorrelated Adversarial Learning for Age-Invariant Face Recognition

There has been an increasing research interest in age-invariant face rec...