Computational perspectives on the other-race effect

Abstract

Psychological studies have long shown that human memory is superior for faces of our own-race than for faces of other-races. In this paper, we review computational studies of own- versus other-race face processing. Computational models examine the visual challenges of representing the uniqueness of individual faces that vary both within and across demographic categories. These models isolate the visual components of the other-race effect and provide an objective control for socioaffective responses to other-race faces. This control allows researchers to compare and test the role of experience/contact in the other-race effect, using various operational definitions of this theoretical construct. The models show that to produce an other-race effect computationally, biased experience or learning must intervene during the process of feature selection. This implicates the critical importance of “developmental” learning in the other-race effect.

Keywords:

• Computational
• Face
• Other-race effect

Thanks are due to funding from the Technical Support Working Group of the Department of Defense, which supported the authors in preparing this paper. Thanks are also due to Allyson Rice and two anonymous reviewers for comments on a previous version of this manuscript.

Thanks are due to funding from the Technical Support Working Group of the Department of Defense, which supported the authors in preparing this paper. Thanks are also due to Allyson Rice and two anonymous reviewers for comments on a previous version of this manuscript.

Notes

¹ Jonathon Phillips was the organizer of the FERET test and so the controls were implemented as baseline algorithms against which the others could be compared.

² We assume this will be covered in detail by Anzures et al. (this issue 2013).

³ Combining was done by rescaling the scores from the different algorithms and averaging them.