EdgeFace: Efficient Face Recognition Model for Edge Devices

In this paper, we present EdgeFace - a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achieves excellent face recognition performance optimized for edge devices. The proposed EdgeFace network not only maintains low computational costs and compact storage, but also achieves high face recognition accuracy, making it suitable for deployment on edge devices. The proposed EdgeFace model achieved the top ranking among models with fewer than 2M parameters in the IJCB 2023 Efficient Face Recognition Competition. Extensive experiments on challenging benchmark face datasets demonstrate the effectiveness and efficiency of EdgeFace in comparison to state-of-the-art lightweight models and deep face recognition models. Our EdgeFace model with 1.77M parameters achieves state of the art results on LFW (99.73%), IJB-B (92.67%), and IJB-C (94.85%), outperforming other efficient models with larger computational complexities. The code to replicate the experiments will be made available publicly.

I. Introduction

Face recognition has become an increasingly active research field, achieving significant recognition accuracy by leveraging breakthroughs in various computer vision tasks through the development of deep neural networks [1], [2], [3] and margin-based loss functions [4], [5], [6], [7], [8], [9], [10]. In spite of remarkable improvements in recognition accuracy, state-of-the-art face recognition models typically involve a deep neural network with a high number of parameters (which requires a large memory) and considerable computational complexity. Considering memory and computational requirements, it is challenging to deploy state-of-the-art face recognition models on resource-constrained devices, such as mobile platforms, robots, embedded systems, etc.