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

TL;DR

This paper introduces TransFace and TransFace++, two novel face recognition frameworks that leverage Vision Transformers and image bytes to improve accuracy, efficiency, and security over traditional CNN-based methods.

Contribution

The paper proposes two new face recognition frameworks using ViTs and image bytes, addressing global feature capture, inference efficiency, and privacy concerns.

Findings

TransFace++ outperforms CNN-based models on popular benchmarks.

The frameworks demonstrate improved accuracy and security.

Code is publicly available for reproducibility.

Abstract

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.