DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition

02/23/2020
by   Hao-Chiang Shao, et al.
22

The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and illumination changes, however, is very expensive, making the diversity of within-class face images a critical issue in practice. In this paper, we propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) that can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. DotFAN is structurally a conditional CycleGAN but has two additional subnetworks, namely face expert network (FEM) and face shape regressor (FSR), for latent code control. While FSR aims to extract face attributes, FEM is designed to capture a face identity. With their aid, DotFAN can learn a disentangled face representation and effectively generate face images of various facial attributes while preserving the identity of augmented faces. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity so that a better face recognition model can be learned from the augmented dataset.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 9

page 10

page 12

research
08/18/2021

SynFace: Face Recognition with Synthetic Data

With the recent success of deep neural networks, remarkable progress has...
research
06/10/2022

Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement

Heterogeneous Face Recognition (HFR) aims to match faces across differen...
research
10/03/2020

3D-Aided Data Augmentation for Robust Face Understanding

Data augmentation has been highly effective in narrowing the data gap an...
research
02/10/2017

Reconstruction-Based Disentanglement for Pose-invariant Face Recognition

Deep neural networks (DNNs) trained on large-scale datasets have recentl...
research
08/05/2022

Analyzing the Impact of Shape Context on the Face Recognition Performance of Deep Networks

In this article, we analyze how changing the underlying 3D shape of the ...
research
05/13/2022

Using Augmented Face Images to Improve Facial Recognition Tasks

We present a framework that uses GAN-augmented images to complement cert...
research
06/14/2020

Disentanglement for Discriminative Visual Recognition

Recent successes of deep learning-based recognition rely on maintaining ...

Please sign up or login with your details

Forgot password? Click here to reset