Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition

by   Hardik Uppal, et al.

We present the Teacher-Student Generative Adversarial Network (TS-GAN) to generate depth images from a single RGB image in order to boost the recognition accuracy of face recognition (FR) systems. For our method to generalize well across unseen datasets, we design two components in the architecture, a teacher and a student. The teacher, which itself consists of a generator and a discriminator, learns a latent mapping between input RGB and paired depth images in a supervised fashion. The student, which consists of two generators (one shared with the teacher) and a discriminator, learns from new RGB data with no available paired depth information, for improved generalization. The fully trained shared generator can then be used in runtime to hallucinate depth from RGB for downstream applications such as face recognition. We perform rigorous experiments to show the superiority of TS-GAN over other methods in generating synthetic depth images. Moreover, face recognition experiments demonstrate that our hallucinated depth along with the input RGB images boosts performance across various architectures when compared to a single RGB modality by average values of +1.2 datasets respectively.



There are no comments yet.


page 6

page 8


High-Accuracy RGB-D Face Recognition via Segmentation-Aware Face Depth Estimation and Mask-Guided Attention Network

Deep learning approaches have achieved highly accurate face recognition ...

Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face

Can faces acquired by low-cost depth sensors be useful to catch some cha...

Distilling portable Generative Adversarial Networks for Image Translation

Despite Generative Adversarial Networks (GANs) have been widely used in ...

ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks

Large-scale face recognition in-the-wild has been recently achieved matu...

Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution

Existing color-guided depth super-resolution (DSR) approaches require pa...

Deep Face Recognition Model Compression via Knowledge Transfer and Distillation

Fully convolutional networks (FCNs) have become de facto tool to achieve...

Distill and De-bias: Mitigating Bias in Face Recognition using Knowledge Distillation

Face recognition networks generally demonstrate bias with respect to sen...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.