A Progressive Learning Framework for Unconstrained Face Recognition
Abstract
The carefully designed backbone network, the increase of training data and the improved training skills have boosted the performance of modern face recognition systems. However, in some deployment cases which aim at model compactness and energy efficiency, some of the existing systems may fail due to the high complexity. Lightweight Face Recognition Challenge is proposed in order to make some progress in this direction and establishes a new comprehensive benchmark. In this challenge, we have designed a light weight backbone architecture and all the parameters are trained in a progressive way. Finally we achieve the 5th in track 1 and the 4th in track 3.
Cite
Text
Chai et al. "A Progressive Learning Framework for Unconstrained Face Recognition." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00331Markdown
[Chai et al. "A Progressive Learning Framework for Unconstrained Face Recognition." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/chai2019iccvw-progressive/) doi:10.1109/ICCVW.2019.00331BibTeX
@inproceedings{chai2019iccvw-progressive,
title = {{A Progressive Learning Framework for Unconstrained Face Recognition}},
author = {Chai, Zhenhua and Li, Shengxi and Meng, Huanhuan and Lai, Shenqi and Wei, Xiaoming and Zhang, Jianwei},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {2703-2710},
doi = {10.1109/ICCVW.2019.00331},
url = {https://mlanthology.org/iccvw/2019/chai2019iccvw-progressive/}
}