To facilitate the research on fairness of face recognition, one can directly download the models and feature vectors of RFW datasets. Note that all of the models are trained by Softmax or Arcface loss without using RL-RBN method.
Due to limited space, we only make Balanced_Softmax avaiable here. Other models and features are put together with our datasets in dropbox or baidu driver, you shoul apply for them through email.
We also have uploaded the evaluation code on RFW, you can directly download them from here and use them to obtain the accuracy on 6000 pairs.• Accuracy_for_RFW.zip. The evaluation code to get accuracy.
Please cite the following if you make use of the dataset.
 Mei Wang, Weihong Deng, Jiani Hu, Xunqiang Tao, Yaohai Huang. Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network. ICCV2019.
 Mei Wang, Yaobin Zhang, Weihong Deng. Meta Balanced Network for Fair Face Recognition. TPAMI 2021.
 Mei Wang, Weihong Deng. Mitigating Bias in Face Recognition using Skewness-Aware Reinforcement Learning. CVPR2020.
 Mei Wang, Weihong Deng. Deep face recognition: A Survey. Neurocomputing.