How (not) to measure bias in face recognition networks

Glüge, Stefan; Amirian, Mohammadreza; Flumini, Dandolo; Stadelmann, Thilo

doi:10.21256/zhaw-20277

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-20277

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	How (not) to measure bias in face recognition networks
Authors:	Glüge, Stefan Amirian, Mohammadreza Flumini, Dandolo Stadelmann, Thilo
et. al:	No
DOI:	10.21256/zhaw-20277 10.1007/978-3-030-58309-5_10
Proceedings:	Artificial Neural Networks in Pattern Recognition
Editors of the parent work:	Schilling, Frank-Peter Stadelmann, Thilo
Conference details:	9th IAPR TC 3 Workshop on Artificial Neural Networks for Pattern Recognition (ANNPR'20), Winterthur, Switzerland, 2-4 September 2020
Issue Date:	2-Sep-2020
Series:	Lecture Notes in Computer Science
Series volume:	12294
Publisher / Ed. Institution:	Springer
Publisher / Ed. Institution:	Cham
Language:	English
Subjects:	Deep learning; Convolutional neural network; Fairness
Subject (DDC):	006: Special computer methods
Abstract:	Within the last years Face Recognition (FR) systems have achieved human-like (or better) performance, leading to extensive deployment in large-scale practical settings. Yet, especially for sensible domains such as FR we expect algorithms to work equally well for everyone, regardless of somebody's age, gender, skin colour and/or origin. In this paper, we investigate a methodology to quantify the amount of bias in a trained Convolutional Neural Network (CNN) model for FR that is not only intuitively appealing, but also has already been used in the literature to argue for certain debiasing methods. It works by measuring the "blindness" of the model towards certain face characteristics in the embeddings of faces based on internal cluster validation measures. We conduct experiments on three openly available FR models to determine their bias regarding race, gender and age, and validate the computed scores by comparing their predictions against the actual drop in face recognition performance for minority cases. Interestingly, we could not link a crisp clustering in the embedding space to a strong bias in recognition rates\|it is rather the opposite. We therefore offer arguments for the reasons behind this observation and argue for the need of a less naive clustering approach to develop a working measure for bias in FR models.
URI:	https://digitalcollection.zhaw.ch/handle/11475/20277
Fulltext version:	Accepted version
License (according to publishing contract):	Licence according to publishing contract
Departement:	Life Sciences and Facility Management School of Engineering
Organisational Unit:	Institute of Applied Information Technology (InIT) Institute of Applied Mathematics and Physics (IAMP) Institute of Computational Life Sciences (ICLS)
Published as part of the ZHAW project:	Libra: A One-Tool Solution for MLD4 Compliance
Appears in collections:	Publikationen Life Sciences und Facility Management Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2020_Gluege-etal_Bias-in-face-recognition-networks_ANNPR.pdf	Accepted Version	3.78 MB	Adobe PDF	View/Open

Show full item record

Glüge, S., Amirian, M., Flumini, D., & Stadelmann, T. (2020). How (not) to measure bias in face recognition networks [Conference paper]. In F.-P. Schilling & T. Stadelmann (Eds.), Artificial Neural Networks in Pattern Recognition. Springer. https://doi.org/10.21256/zhaw-20277

Glüge, S. et al. (2020) ‘How (not) to measure bias in face recognition networks’, in F.-P. Schilling and T. Stadelmann (eds) Artificial Neural Networks in Pattern Recognition. Cham: Springer. Available at: https://doi.org/10.21256/zhaw-20277.

S. Glüge, M. Amirian, D. Flumini, and T. Stadelmann, “How (not) to measure bias in face recognition networks,” in Artificial Neural Networks in Pattern Recognition, Sep. 2020. doi: 10.21256/zhaw-20277.

GLÜGE, Stefan, Mohammadreza AMIRIAN, Dandolo FLUMINI und Thilo STADELMANN, 2020. How (not) to measure bias in face recognition networks. In: Frank-Peter SCHILLING und Thilo STADELMANN (Hrsg.), Artificial Neural Networks in Pattern Recognition. Conference paper. Cham: Springer. 2 September 2020

Glüge, Stefan, Mohammadreza Amirian, Dandolo Flumini, and Thilo Stadelmann. 2020. “How (Not) to Measure Bias in Face Recognition Networks.” Conference paper. In Artificial Neural Networks in Pattern Recognition, edited by Frank-Peter Schilling and Thilo Stadelmann. Cham: Springer. https://doi.org/10.21256/zhaw-20277.

Glüge, Stefan, et al. “How (Not) to Measure Bias in Face Recognition Networks.” Artificial Neural Networks in Pattern Recognition, edited by Frank-Peter Schilling and Thilo Stadelmann, Springer, 2020, https://doi.org/10.21256/zhaw-20277.