Central Difference Convolutional Networks

CDCN

Main code of CVPR2020 paper “Searching Central Difference Convolutional Networks for Face Anti-Spoofing”

Based on the Central Difference Convolution (CDC) and Contrastive Depth Loss (CDL), we achieved

1st Place in ChaLearn Multi-Modal Face Anti-spoofing Attack Detection Challenge @CVPR2020

2nd Place in ChaLearn Single-Modal(RGB) Face Anti-spoofing Attack Detection Challenge @CVPR2020

It is just for research purpose, and commercial use is not allowed.

Citation

If you use the CDCN or CDL, please cite these three papers:

@inproceedings{yu2020searching,
    title={Searching Central Difference Convolutional Networks for Face Anti-Spoofing},
    author={Yu, Zitong and Zhao, Chenxu and Wang, Zezheng and Qin, Yunxiao and Su, Zhuo and Li, Xiaobai and Zhou, Feng and Zhao, Guoying},
    booktitle= {CVPR},
    year = {2020}
}

@inproceedings{wang2020deep,
    title={Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing},
    author={Wang, Zezheng and Yu, Zitong and Zhao, Chenxu and Zhu, Xiangyu and Qin, Yunxiao and Zhou, Qiusheng and Zhou, Feng and Lei, Zhen},
    booktitle= {CVPR (Oral)},
    year = {2020}
}

@inproceedings{qin2019learning,
    title={Learning Meta Model for Zero-and Few-shot Face Anti-spoofing},
    author={Qin, Yunxiao and Zhao, Chenxu and Zhu, Xiangyu and Wang, Zezheng and Yu, Zitong and Fu, Tianyu and Zhou, Feng and Shi, Jingping and Lei, Zhen},
    booktitle= {AAAI},
    year = {2020}
}