IFRT is a globalised fair benchmark for face recognition algorithms.
IFRT evaluates the algorithm performance on worldwide web pictures which contain various sex, age and race groups.
IFRT testset consists of non-celebrities so we can ensure that it has very few overlap with public available
face recognition training set, such as MS1M and CASIA as they mostly collected from online celebrities.
As the result, we can evaluate the FAIR performance for different algorithms.
Similar to FRVT, we encourage participants to prepare a black-box feature extractor. To simplify this process, trained ArcFace models are also allowed.