Official Implementation
for the paper Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers (WACV 2023) by Hai Phan, Cindy Le, Vu Le, Yihui He, and Anh Nguyen.
If you use this software, please consider citing:
@article{hai2023facevit,
title={Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers},
author={Hai Phan, Cindy Le, Vu Le, Yihui He, Anh Nguyen},
journal={arXiv preprint arXiv:2311.02803},
year={2023}
}
Python >= 3.5
Pytorch > 1.0
Opencv >= 3.4.4
pip install tqmd
pip install mxnet
pip install wandb
-
Download LFW, out-of-distribution (OOD) LFW test sets: Google Drive
-
Download CASIA for training: Here
-
Download pretrained models:
-
Download arranged pairs: Google Drive
-
Create the following folders:
mkdir results
mkdir pretrained
Then put pretrained models to results
folder and pretrained
for testing and training, respectively.
-
Training: Revise directory in
train.py
andconfig.py
with your own directory. Then, runpython train.py
-
Testing: Revise directory in
test.py
with your own directory. Then, runpython test.py
MIT
- W. Zhao, Y. Rao, Z. Wang, J. Lu, Zhou. Towards interpretable deep metric learning with structural matching, ICCV 2021 DIML
- J. Deng, J. Guo, X. Niannan, and StefanosZafeiriou. Arcface: Additive angular margin loss for deepface recognition, CVPR 2019 Arcface Pytorch
- H. Phan, A. Nguyen. DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover’s Distance Improves Out-Of-Distribution Face Identification, CVPR 2022 DeepFace-EMD
- F. Schroff, D. Kalenichenko, J. Philbin. Facenet: A unified embedding for face recognition and clustering. CVPR 2015 FaceNet Pytorch
- L. Weiyang, W. Yandong, Y. Zhiding, L. Ming, R. Bhiksha, S. Le. SphereFace: Deep Hypersphere Embedding for Face Recognition, CVPR 2017 sphereface, sphereface pytorch
- Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen. Deepemd: Differentiable earth mover’s distance for few-shotlearning, CVPR 2020 paper