Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
This work tackles the problem of ensuring accurate and fair performance evaluation in high-stakes applications like face recognition, though it is incremental as it builds on existing ROC analysis methods.
The paper addresses the need for reliable uncertainty assessment in ROC curve analysis for similarity scoring functions, particularly in face recognition, by proving asymptotic guarantees for empirical ROC curves and fairness metrics, and demonstrating through experiments on real datasets that a dedicated recentering technique outperforms naive bootstrap methods.
The ROC curve is the major tool for assessing not only the performance but also the fairness properties of a similarity scoring function. In order to draw reliable conclusions based on empirical ROC analysis, accurately evaluating the uncertainty level related to statistical versions of the ROC curves of interest is absolutely necessary, especially for applications with considerable societal impact such as Face Recognition. In this article, we prove asymptotic guarantees for empirical ROC curves of similarity functions as well as for by-product metrics useful to assess fairness. We also explain that, because the false acceptance/rejection rates are of the form of U-statistics in the case of similarity scoring, the naive bootstrap approach may jeopardize the assessment procedure. A dedicated recentering technique must be used instead. Beyond the theoretical analysis carried out, various experiments using real face image datasets provide strong empirical evidence of the practical relevance of the methods promoted here, when applied to several ROC-based measures such as popular fairness metrics.