Implementation-ArcFace-in-MATLAB

Version 1.1.1 (88.1 MB) by Nobuaki Fukuchi

This is implementatoin of ArcFace(https://arxiv.org/abs/1801.07698) in MATLAB. In this demo, train and test pet images by using ArcFace.

https://github.com/fukuchi0105/Implementation-ArcFace-in-MATLAB

0.0

(0)

67 Downloads

Updated 3 Mar 2022

View License on GitHub

ArcFace_MATLAB

This is implementatoin of ArcFace(https://arxiv.org/abs/1801.07698) in MATLAB. In this demo, train and test pet images by using ArcFace. This network can

calculate the similarity between your pet images and each breed of dogs and cats.
calculate the similarity between your pet images and the other pet images.

Products used in development

MATLAB R2021b
Image Processing Toolbox
Deep Learning Toolbox
add on: Deep Learning Toolbox Model for ResNet-50 Network
Parallel Computing Toolbox (if you want to use GPU in training)

Setup

dataset: Datasets is automatically downloaded from Oxford-IIIT Pet Datset(https://www.robots.ox.ac.uk/~vgg/data/pets/).

To Run:
・Train and Test:(GPU is recommanded)
　1．Open arcface_train.mlx
　2. Change directory to "arcface_demo"
　3. Execute Run
・Test:
　1．Open arcface_train.mlx
　2. Change directory to "arcface_demo"
　3. Go to "Test Model" Section
　　 If you want to use train model by run, remove commnet of "load dlnet_end.mat"
　4．Run section of "Test Model"

Getting Started

Please open arcface_train.mlx　and read instructions

Examples

To learn how to use this in testing workflows, see arface_train.mlx.

License

The license for Implementation-ArcFace-in-MATLAB is available in the license.txt file in this GitHub repository.

Include any other License information here, including third-party content using separate license agreements

Community Support

MATLAB Central

Cite As

Nobuaki Fukuchi (2025). Implementation-ArcFace-in-MATLAB (https://github.com/fukuchi0105/Implementation-ArcFace-in-MATLAB/releases/tag/v1.1.1), GitHub. Retrieved November 18, 2025.

Deng, Jiankang, et al. “ArcFace: Additive Angular Margin Loss for Deep Face Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers (IEEE), 2021, pp. 1–1, doi:10.1109/tpami.2021.3087709.

View more styles

MATLAB Release Compatibility

Created with R2021b

Compatible with any release

Platform Compatibility

Windows macOS Linux

Tags Add Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

ArcFaceLayer.m

Version	Published	Release Notes
1.1.1	3 Mar 2022	See release notes for this release on GitHub: https://github.com/fukuchi0105/Implementation-ArcFace-in-MATLAB/releases/tag/v1.1.1	Download
1.1.0	3 Mar 2022		Download
1.0.0.0	28 Sep 2022	See release notes for this release on GitHub: https://github.com/fukuchi0105/Implementation-ArcFace-in-MATLAB/releases/tag/v1.0.0	Download

To view or report issues in this GitHub add-on, visit the GitHub Repository.

MLA	Deng, Jiankang, et al. “ArcFace: Additive Angular Margin Loss for Deep Face Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers (IEEE), 2021, pp. 1–1, doi:10.1109/tpami.2021.3087709.
APA	Deng, J., Guo, J., Yang, J., Xue, N., Cotsia, I., & Zafeiriou, S. P. (2021). ArcFace: Additive Angular Margin Loss for Deep Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–1. Institute of Electrical and Electronics Engineers (IEEE). Retrieved from https://doi.org/10.1109%2Ftpami.2021.3087709
BibTeX	@article{Deng_2021, doi = {10.1109/tpami.2021.3087709}, url = {https://doi.org/10.1109%2Ftpami.2021.3087709}, year = 2021, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, pages = {1--1}, author = {Jiankang Deng and Jia Guo and Jing Yang and Niannan Xue and Irene Cotsia and Stefanos P Zafeiriou}, title = {{ArcFace}: Additive Angular Margin Loss for Deep Face Recognition}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} }