Face Recognition: Too Bias, or Not Too Bias?

By Joseph P. Robinson, Gennady Livitz, Yann Henon, Can Qin, Yun Raymond Fu, Samson Timoner. 2020

149 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

In Signal Processing

Citations in the corpus

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation (2021, background): “It is of course especially important to be careful when the system concerns humans, for example with biases relating to human ethnicity and gender in facial recognition systems (Klare et al., 2012; Robinson et al., 2020).”
One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision (2021, methodology): “We use four fair computer vision datasets: FairFace [28], BFW [41], RFW [49], and LAOFIW [2].”