TL;DR该论文提出利用深层学习方式进行人脸识别，通过生成对抗网络 GAN 生成虚拟多样的人脸数据集，以减小数据集的偏差对模型预测性能的影响。
Abstract
facial recognition systems have made significant strides thanks to data-heavy
deep learning models, but these models rely on large privacy-sensitive
datasets. Unfortunately, many of these datasets lack diversity