Balancing Beyond Discrete Categories: Continuous Demographic Labels for Fair Face Recognition
This addresses fairness issues in face recognition for diverse populations, offering an incremental improvement over existing bias mitigation methods.
The paper tackles bias in face recognition by proposing to treat ethnicity labels as continuous variables rather than discrete categories, showing that models trained on datasets balanced in this continuous space outperform those balanced discretely.
Bias has been a constant in face recognition models. Over the years, researchers have looked at it from both the model and the data point of view. However, their approach to mitigation of data bias was limited and lacked insight on the real nature of the problem. Here, in this document, we propose to revise our use of ethnicity labels as a continuous variable instead of a discrete value per identity. We validate our formulation both experimentally and theoretically, showcasing that not all identities from one ethnicity contribute equally to the balance of the dataset; thus, having the same number of identities per ethnicity does not represent a balanced dataset. We further show that models trained on datasets balanced in the continuous space consistently outperform models trained on data balanced in the discrete space. We trained more than 65 different models, and created more than 20 subsets of the original datasets.