SynFace: Face Recognition with Synthetic Data

08/18/2021
by   Haibo Qiu, et al.
22

With the recent success of deep neural networks, remarkable progress has been achieved on face recognition. However, collecting large-scale real-world training data for face recognition has turned out to be challenging, especially due to the label noise and privacy issues. Meanwhile, existing face recognition datasets are usually collected from web images, lacking detailed annotations on attributes (e.g., pose and expression), so the influences of different attributes on face recognition have been poorly investigated. In this paper, we address the above-mentioned issues in face recognition using synthetic face images, i.e., SynFace. Specifically, we first explore the performance gap between recent state-of-the-art face recognition models trained with synthetic and real face images. We then analyze the underlying causes behind the performance gap, e.g., the poor intra-class variations and the domain gap between synthetic and real face images. Inspired by this, we devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the above performance gap, demonstrating the great potentials of synthetic data for face recognition. Furthermore, with the controllable face synthesis model, we can easily manage different factors of synthetic face generation, including pose, expression, illumination, the number of identities, and samples per identity. Therefore, we also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.

READ FULL TEXT

page 1

page 5

page 12

page 13

research
02/16/2018

Training Deep Face Recognition Systems with Synthetic Data

Recent advances in deep learning have significantly increased the perfor...
research
10/05/2022

DigiFace-1M: 1 Million Digital Face Images for Face Recognition

State-of-the-art face recognition models show impressive accuracy, achie...
research
02/23/2020

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

The performance of a convolutional neural network (CNN) based face recog...
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
04/10/2018

Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model

We propose a novel end-to-end semi-supervised adversarial framework to g...
research
05/20/2022

Towards the Generation of Synthetic Images of Palm Vein Patterns: A Review

With the recent success of computer vision and deep learning, remarkable...
research
04/14/2023

DCFace: Synthetic Face Generation with Dual Condition Diffusion Model

Generating synthetic datasets for training face recognition models is ch...

Please sign up or login with your details

Forgot password? Click here to reset