Light weight face recognition models including data augmentation, Arcface and focal loss. It is a sample code for Lightweight Face Recognition competition ICCV2019.

🚩 OCTOBER 2019: In The Lightweight Face Recognition Challenge & Workshop at International Conference on Computer Vision (ICCV) 2019, Seoul Korea, our team won the first place in both track 1 (1G FLOPs face recognition challenge) and track 2 (30G FLOPs face recognition challenge) and was awarded Special Innovation by the committee.

• Python 3.7
• Pytorch 1.1
• CUDA 10.0
• opencv
• numpy
• pillow

• ResNet
• MobileNet
• EfficientNet

@InProceedings{Cheng_2019_ICCV_Workshops,
author = {Cheng, Yu and Li, Yanfeng and Liu, Qiankun and Yao, Yuan and Sai Vijay Kumar Pedapudi, Venkata and Fan, Xiaotian and Su, Chi and Shen, Shengmei},
title = {A Graph Based Unsupervised Feature Aggregation for Face Recognition},
booktitle = {The IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}