Face Recognition: Too Bias, or Not Too Bias?

Joseph P. Robinson, Gennady Livitz, Yann Henon, Can Qin, Yun Fu, Samson Timoner

Abstract

We reveal critical insights into problems of bias in state-of-the-art facial recognition (FR) systems using a novel Balanced Faces in the Wild (BFW) dataset: data balanced for gender and ethnic groups. We show variations in the optimal scoring threshold for face-pairs across different subgroups. Thus, the conventional approach of learning a global threshold for all pairs results in performance gaps between subgroups. By learning subgroup-specific thresholds, we reduce performance gaps, and also show a notable boost in overall performance. Furthermore, we do a human evaluation to measure bias in humans, which supports the hypothesis that an analogous bias exists in human perception. For the BFW database, source code, and more, visit https://github.com/visionjo/facerec-bias-bfw.
BibTeX
@inproceedings{robinson2020face,
  author = {Joseph P. Robinson and Gennady Livitz and Yann Henon and Can Qin and Yun Fu and Samson Timoner},
  title = {{Face Recognition: Too Bias, or Not Too Bias?}},
  booktitle = {Workshops @ CVPR},
  year = {2020},
  doi = {10.1109/cvprw50498.2020.00008},
}
Figure