Increasing Fairness in Classification of Out of Distribution Data for Facial Recognition

arXiv:2404.03876v1 Announce Type: cross
Abstract: Standard classification theory assumes that the distribution of images in the test and training sets are identical. Unfortunately, real-life scenarios typically feature unseen data ("out-of-distribution data") which is different from data in the training distribution("in-distribution"). This issue is most prevalent in social justice problems where data from under-represented groups may appear in the test data without representing an equal proportion of the training data. This may result in a model returning confidently wrong decisions and …

abstract arxiv classification cs.cv cs.cy cs.lg data distribution facial recognition fairness feature images issue justice life recognition social social justice standard test theory training type