EdgeFace: Efficient Face Recognition Model for Edge Devices

Anjith George1 and Christophe Ecabert1 and Hatef Otroshi Shahreza1,2 and Ketan Kotwal1 and Sébastien Marcel1,3
1Idiap Research Institute, 2EPFL, 3UNIL

🏆 Winner of IJCB 2023 Efficient Face Recognition Competition 🏆
Paper arXiv Code
Model architecture

Model architecture of EdgeFace model.

Summary

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.

Performance of the models

The performance of the EdgeFace models on the standard face recognition benchmarks are shown here, our models ranked first in the compact track in the IJCB 2023 Efficient Face Recognition Competition.

Performance of teh EdgeFace models

The performance of the EdgeFace models on the standard face recognition benchmarks.


🏆 Winner of IJCB 2023 Efficient Face Recognition Competition

Given the performance of our model, EdgeFace achieved the first rank in Compact Track of IJCB 2023 Efficient Face Recognition Competition:

IJCB 2023 Efficient Face Recognition Competition Certificate

IJCB 2023 Efficient Face Recognition Competition Certificate for EdgeFace as the first (winner) solution.

Reproducibility: Source Code

The source code and pretrained models are available in the following GitLab repository.

BibTeX


@article{george2024edgeface,
  title={EdgeFace: Efficient Face Recognition Model for Edge Devices},
  author={George, Anjith and Ecabert, Christophe and Shahreza, Hatef Otroshi and Kotwal, Ketan and Marcel, S{\'e}bastien},
  journal={IEEE Transactions on Biometrics, Behavior, and Identity Science},
  year={2024},
  publisher={IEEE}
}