Considering Race a Problem of Transfer Learning
This addresses fairness and accuracy issues in biometric systems for diverse populations, but it is incremental as it applies existing transfer learning concepts to race-specific domains.
The paper tackles performance disparities in biometric applications across racial subgroups by framing race as a transfer learning boundary for facial classification and image synthesis, demonstrating improved classification transfer and showing that GANs trained on one race perform poorly on another using a new race annotation for CelebA.
As biometric applications are fielded to serve large population groups, issues of performance differences between individual sub-groups are becoming increasingly important. In this paper we examine cases where we believe race is one such factor. We look in particular at two forms of problem; facial classification and image synthesis. We take the novel approach of considering race as a boundary for transfer learning in both the task (facial classification) and the domain (synthesis over distinct datasets). We demonstrate a series of techniques to improve transfer learning of facial classification; outperforming similar models trained in the target's own domain. We conduct a study to evaluate the performance drop of Generative Adversarial Networks trained to conduct image synthesis, in this process, we produce a new annotation for the Celeb-A dataset by race. These networks are trained solely on one race and tested on another - demonstrating the subsets of the CelebA to be distinct domains for this task.