TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dan, Jun, Liu, Yang, Sun, Baigui, Deng, Jiankang, Luo, Shan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918170196967424
author Dan, Jun
Liu, Yang
Sun, Baigui
Deng, Jiankang
Luo, Shan
author_facet Dan, Jun
Liu, Yang
Sun, Baigui
Deng, Jiankang
Luo, Shan
contents Face Recognition (FR) technology has made significant strides with the emergence of deep learning. Typically, most existing FR models are built upon Convolutional Neural Networks (CNN) and take RGB face images as the model's input. In this work, we take a closer look at existing FR paradigms from high-efficiency, security, and precision perspectives, and identify the following three problems: (i) CNN frameworks are vulnerable in capturing global facial features and modeling the correlations between local facial features. (ii) Selecting RGB face images as the model's input greatly degrades the model's inference efficiency, increasing the extra computation costs. (iii) In the real-world FR system that operates on RGB face images, the integrity of user privacy may be compromised if hackers successfully penetrate and gain access to the input of this model. To solve these three issues, we propose two novel FR frameworks, i.e., TransFace and TransFace++, which successfully explore the feasibility of applying ViTs and image bytes to FR tasks, respectively. Experiments on popular face benchmarks demonstrate the superiority of our TransFace and TransFace++. Code is available at https://github.com/DanJun6737/TransFace_pp.
format Preprint
id arxiv_https___arxiv_org_abs_2308_10133
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security
Dan, Jun
Liu, Yang
Sun, Baigui
Deng, Jiankang
Luo, Shan
Computer Vision and Pattern Recognition
Artificial Intelligence
Face Recognition (FR) technology has made significant strides with the emergence of deep learning. Typically, most existing FR models are built upon Convolutional Neural Networks (CNN) and take RGB face images as the model's input. In this work, we take a closer look at existing FR paradigms from high-efficiency, security, and precision perspectives, and identify the following three problems: (i) CNN frameworks are vulnerable in capturing global facial features and modeling the correlations between local facial features. (ii) Selecting RGB face images as the model's input greatly degrades the model's inference efficiency, increasing the extra computation costs. (iii) In the real-world FR system that operates on RGB face images, the integrity of user privacy may be compromised if hackers successfully penetrate and gain access to the input of this model. To solve these three issues, we propose two novel FR frameworks, i.e., TransFace and TransFace++, which successfully explore the feasibility of applying ViTs and image bytes to FR tasks, respectively. Experiments on popular face benchmarks demonstrate the superiority of our TransFace and TransFace++. Code is available at https://github.com/DanJun6737/TransFace_pp.
title TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2308.10133