Timezone: »
The ROC curve is the major tool for assessing not only the performance but also the fairness properties of a similarity scoring function in Face Recognition. In order to draw reliable conclusions based on empirical ROC analysis, evaluating accurately the uncertainty related to statistical versions of the ROC curves of interest is necessary. For this purpose, we explain in this paper that, because the True/False Acceptance Rates are of the form of U-statistics in the case of similarity scoring, the naive bootstrap approach is not valid here and that a dedicated recentering technique must be used instead. This is illustrated on real data of face images, when applied to several ROC-based metrics such as popular fairness metrics.
Author Information
Jean-Rémy Conti (Télécom Paris Idemia)
Stéphan Clémençon (Telecom ParisTech)
More from the Same Authors
-
2017 Poster: Ranking Data with Continuous Labels through Oriented Recursive Partitions »
Stéphan Clémençon · Mastane Achab -
2015 Poster: SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk »
Guillaume Papa · Stéphan Clémençon · Aurélien Bellet -
2015 Poster: Extending Gossip Algorithms to Distributed Estimation of U-statistics »
Igor Colin · Aurélien Bellet · Joseph Salmon · Stéphan Clémençon -
2015 Spotlight: Extending Gossip Algorithms to Distributed Estimation of U-statistics »
Igor Colin · Aurélien Bellet · Joseph Salmon · Stéphan Clémençon -
2011 Poster: On U-processes and clustering performance »
Stéphan Clémençon -
2011 Spotlight: On U-processes and clustering performance »
Stéphan Clémençon -
2009 Poster: AUC optimization and the two-sample problem »
Stéphan Clémençon · Nicolas Vayatis · Marine Depecker