EdgeFace: Efficient Face Recognition Model for Edge Devices

TL;DR

EdgeFace is a lightweight, hybrid CNN-Transformer face recognition model optimized for edge devices, achieving high accuracy with low computational cost and outperforming larger models on benchmark datasets.

Contribution

We introduce EdgeFace, a novel hybrid architecture combining CNN and Transformer elements with low rank layers, optimized for efficient face recognition on edge devices.

Findings

Achieves 99.73% on LFW with 1.77M parameters.

Outperforms state-of-the-art lightweight models on benchmark datasets.

Maintains high accuracy with low computational complexity.

Abstract

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. 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.