TransFace++

• Code for the following papers:

(1) [ICCV-2023] TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective. (Conference version)[Code in FaceChain Rep.] [CODE] [ModelScope] [阿里云] [CVer] [CSDN]

(2) [TPAMI-2025] TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Efficiency, Security, and Precision. [Arxiv Version]

Codes for TransFace and TransFace++ models are respectively in folders TransFace and TransFace++.

Citation

• If you find it helpful for you, please cite our paper

@inproceedings{dan2023transface,
  title={TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective},
  author={Dan, Jun and Liu, Yang and Xie, Haoyu and Deng, Jiankang and Xie, Haoran and Xie, Xuansong and Sun, Baigui},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={20642--20653},
  year={2023}
}

@article{dan2025transface++,
  title={TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security},
  author={Dan, Jun and Liu, Yang and Sun, Baigui and Deng, Jiankang and Luo, Shan},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2025},
  publisher={IEEE}
}

Acknowledgments

We thank Insighface for the excellent code base.