TU Darmstadt / ULB / TUbiblio

Reliable Age and Gender Estimation from Face Images: Stating the Confidence of Model Predictions

Terhorst, Philipp and Huber, Marco and Kolf, Jan Niklas and Zelch, Ines and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan (2019):
Reliable Age and Gender Estimation from Face Images: Stating the Confidence of Model Predictions.
pp. 1-8, IEEE, 10th International Conference on Biometrics Theory, Applications and Systems (BTAS 2019), Tampa, USA, 23.-26.09., ISBN 978-1-7281-1523-8,
DOI: 10.1109/BTAS46853.2019.9185975,
[Conference or Workshop Item]

Abstract

Automated age and gender estimation became of great importance for many potential applications ranging from forensics to social media. Although previous works reported high increased performances, these solutions tend to mispredict under challenging conditions or when the trained model faces a sample that was underrepresented in the training data. In this work, we propose an age and gender estimation model, as well as a novel reliability measure to quantify the confidence of the model’s prediction. Our solution is based on stochastic forward passes through dropout-reduced neural networks that were theoretically proven to approximate Gaussian processes. By utilizing multiple stochastic forward passes, the centrality and dispersion of these predictions are used to derive a confidence statement about the prediction. Experiments were conducted on the Adience benchmark. We showed that the proposed solution reached and exceeded state-ofthe-art performance. Further, we demonstrated that the proposed reliability measure correlates with the prediction performance and thus, is highly successful in quantifying the prediction reliability.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Terhorst, Philipp and Huber, Marco and Kolf, Jan Niklas and Zelch, Ines and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan
Title: Reliable Age and Gender Estimation from Face Images: Stating the Confidence of Model Predictions
Language: English
Abstract:

Automated age and gender estimation became of great importance for many potential applications ranging from forensics to social media. Although previous works reported high increased performances, these solutions tend to mispredict under challenging conditions or when the trained model faces a sample that was underrepresented in the training data. In this work, we propose an age and gender estimation model, as well as a novel reliability measure to quantify the confidence of the model’s prediction. Our solution is based on stochastic forward passes through dropout-reduced neural networks that were theoretically proven to approximate Gaussian processes. By utilizing multiple stochastic forward passes, the centrality and dispersion of these predictions are used to derive a confidence statement about the prediction. Experiments were conducted on the Adience benchmark. We showed that the proposed solution reached and exceeded state-ofthe-art performance. Further, we demonstrated that the proposed reliability measure correlates with the prediction performance and thus, is highly successful in quantifying the prediction reliability.

Publisher: IEEE
ISBN: 978-1-7281-1523-8
Uncontrolled Keywords: Biometrics, Face recognition, Facial expression analysis
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 Title: 10th International Conference on Biometrics Theory, Applications and Systems (BTAS 2019)
Event Location: Tampa, USA
Event Dates: 23.-26.09.
Date Deposited: 22 Sep 2020 10:08
DOI: 10.1109/BTAS46853.2019.9185975
Official URL: https://doi.org/10.1109/BTAS46853.2019.9185975
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