TU Darmstadt / ULB / TUbiblio

Post-comparison mitigation of demographic bias in face recognition using fair score normalization

Terhörst, Philipp and Kolf, Jan Niklas and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan (2020):
Post-comparison mitigation of demographic bias in face recognition using fair score normalization.
In: Pattern Recognition Letters, 140, pp. 332-338. Elsevier, ISSN 0167-8655,
DOI: 10.1016/j.patrec.2020.11.007,
[Article]

Abstract

Current face recognition systems achieve high progress on several benchmark tests. Despite this progress, recent works showed that these systems are strongly biased against demographic sub-groups. Consequently, an easily integrable solution is needed to reduce the discriminatory effect of these biased systems. Previous work mainly focused on learning less biased face representations, which comes at the cost of a strongly degraded overall recognition performance. In this work, we propose a novel unsupervised fair score normalization approach that is specifically designed to reduce the effect of bias in face recognition and subsequently lead to a significant overall performance boost. Our hypothesis is built on the notation of individual fairness by designing a normalization approach that leads to treating “similar” individuals “similarly”. Experiments were conducted on three publicly available datasets captured under controlled and in-the-wild circumstances. Results demonstrate that our solution reduces demographic biases, e.g. by up to 82.7% in the case when gender is considered. Moreover, it mitigates the bias more consistently than existing works. In contrast to previous works, our fair normalization approach enhances the overall performance by up to 53.2% at false match rate of 10−3 and up to 82.9% at a false match rate of 10−5. Additionally, it is easily integrable into existing recognition systems and not limited to face biometrics.

Item Type: Article
Erschienen: 2020
Creators: Terhörst, Philipp and Kolf, Jan Niklas and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan
Title: Post-comparison mitigation of demographic bias in face recognition using fair score normalization
Language: English
Abstract:

Current face recognition systems achieve high progress on several benchmark tests. Despite this progress, recent works showed that these systems are strongly biased against demographic sub-groups. Consequently, an easily integrable solution is needed to reduce the discriminatory effect of these biased systems. Previous work mainly focused on learning less biased face representations, which comes at the cost of a strongly degraded overall recognition performance. In this work, we propose a novel unsupervised fair score normalization approach that is specifically designed to reduce the effect of bias in face recognition and subsequently lead to a significant overall performance boost. Our hypothesis is built on the notation of individual fairness by designing a normalization approach that leads to treating “similar” individuals “similarly”. Experiments were conducted on three publicly available datasets captured under controlled and in-the-wild circumstances. Results demonstrate that our solution reduces demographic biases, e.g. by up to 82.7% in the case when gender is considered. Moreover, it mitigates the bias more consistently than existing works. In contrast to previous works, our fair normalization approach enhances the overall performance by up to 53.2% at false match rate of 10−3 and up to 82.9% at a false match rate of 10−5. Additionally, it is easily integrable into existing recognition systems and not limited to face biometrics.

Journal or Publication Title: Pattern Recognition Letters
Journal volume: 140
Publisher: Elsevier
Uncontrolled Keywords: Biometrics, Bias, Face recognition, Machine learning, Deep learning
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Date Deposited: 25 Jan 2021 11:34
DOI: 10.1016/j.patrec.2020.11.007
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