TU Darmstadt / ULB / TUbiblio

Comparison-Level Mitigation of Ethnic Bias in Face Recognition

Terhorst, Philipp and Tran, Mai Ly and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan (2020):
Comparison-Level Mitigation of Ethnic Bias in Face Recognition.
In: 2020 8th International Workshop on Biometrics and Forensics (IWBF), pp. 1-6,
Los Alamitos, Calif., Porto, Portugal, 29-30 April 2020, DOI: 10.1109/IWBF49977.2020.9107956,
[Conference or Workshop Item]

Abstract

Current face recognition systems achieve high performance on several benchmark tests. Despite this progress,recent works showed that these systems are strongly biasedagainst demographic sub-groups. Previous works introducedapproaches that aim at learning less biased representations.However, applying these approaches in real applications requiresa complete replacement of the templates in the database. Thisreplacement procedure further requires that a face image ofeach enrolled individual is stored as well. In this work, wepropose the first bias-mitigating solution that works on thecomparison-level of a biometric system. We propose a fairnessdriven neural network classifier for the comparison of twobiometric templates to replace the systems similarity function.This fair classifier is trained with a novel penalization termin the loss function to introduce the criteria of group andindividual fairness to the decision process. This penalization termforces the score distributions of different ethnicities to be similar,leading to a reduction of the intra-ethnic performance differences.Experiments were conducted on two publicly available datasetsand evaluated the performance of four different ethnicities. Theresults showed that for both fairness criteria, our proposedapproach is able to significantly reduce the ethnic bias, whileit preserves a high recognition ability. Our model, build onindividual fairness, achieves bias reduction rate between 15.35%and 52.67%. In contrast to previous work, our solution is easy tointegrate into existing systems by simply replacing the systemssimilarity functions with our fair template comparison approach.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Terhorst, Philipp and Tran, Mai Ly and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan
Title: Comparison-Level Mitigation of Ethnic Bias in Face Recognition
Language: English
Abstract:

Current face recognition systems achieve high performance on several benchmark tests. Despite this progress,recent works showed that these systems are strongly biasedagainst demographic sub-groups. Previous works introducedapproaches that aim at learning less biased representations.However, applying these approaches in real applications requiresa complete replacement of the templates in the database. Thisreplacement procedure further requires that a face image ofeach enrolled individual is stored as well. In this work, wepropose the first bias-mitigating solution that works on thecomparison-level of a biometric system. We propose a fairnessdriven neural network classifier for the comparison of twobiometric templates to replace the systems similarity function.This fair classifier is trained with a novel penalization termin the loss function to introduce the criteria of group andindividual fairness to the decision process. This penalization termforces the score distributions of different ethnicities to be similar,leading to a reduction of the intra-ethnic performance differences.Experiments were conducted on two publicly available datasetsand evaluated the performance of four different ethnicities. Theresults showed that for both fairness criteria, our proposedapproach is able to significantly reduce the ethnic bias, whileit preserves a high recognition ability. Our model, build onindividual fairness, achieves bias reduction rate between 15.35%and 52.67%. In contrast to previous work, our solution is easy tointegrate into existing systems by simply replacing the systemssimilarity functions with our fair template comparison approach.

Title of Book: 2020 8th International Workshop on Biometrics and Forensics (IWBF)
Place of Publication: Los Alamitos, Calif.
Uncontrolled Keywords: Biometrics, Face recognition
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Location: Porto, Portugal
Event Dates: 29-30 April 2020
Date Deposited: 08 Jun 2020 10:18
DOI: 10.1109/IWBF49977.2020.9107956
Official URL: https://doi.org/10.1109/IWBF49977.2020.9107956
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details