Enhancing Facial Data Diversity with Style-based Face Aging
This addresses fairness issues in face recognition algorithms by mitigating age bias, though it is incremental as it focuses on a specific attribute.
The paper tackles the problem of dataset bias in face datasets by increasing age diversity through a novel generative style-based architecture for data augmentation, showing it outperforms state-of-the-art methods in age transfer and significantly enhances dataset diversity metrics.
A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. If not mitigated, bias leads to algorithms that exhibit unfair behaviour towards such groups. In this work, we address the problem of increasing the diversity of face datasets with respect to age. Concretely, we propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns by conditioning on multi-resolution age-discriminative representations. By evaluating on several age-annotated datasets in both single- and cross-database experiments, we show that the proposed method outperforms state-of-the-art algorithms for age transfer, especially in the case of age groups that lie in the tails of the label distribution. We further show significantly increased diversity in the augmented datasets, outperforming all compared methods according to established metrics.