TU Darmstadt / ULB / TUbiblio

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

Terhörst, Philipp ; Huber, Marco ; Kolf, Jan Niklas ; Zelch, Ines ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan (2019)
Reliable Age and Gender Estimation from Face Images: Stating the Confidence of Model Predictions.
10th International Conference on Biometrics Theory, Applications and Systems (BTAS 2019). Tampa, USA (23.-26.09.)
doi: 10.1109/BTAS46853.2019.9185975
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (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.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2019
Autor(en): Terhörst, Philipp ; Huber, Marco ; Kolf, Jan Niklas ; Zelch, Ines ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan
Art des Eintrags: Bibliographie
Titel: Reliable Age and Gender Estimation from Face Images: Stating the Confidence of Model Predictions
Sprache: Englisch
Publikationsjahr: 3 September 2019
Verlag: IEEE
Veranstaltungstitel: 10th International Conference on Biometrics Theory, Applications and Systems (BTAS 2019)
Veranstaltungsort: Tampa, USA
Veranstaltungsdatum: 23.-26.09.
DOI: 10.1109/BTAS46853.2019.9185975
URL / URN: https://doi.org/10.1109/BTAS46853.2019.9185975
Kurzbeschreibung (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.

Freie Schlagworte: Biometrics, Face recognition, Facial expression analysis
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing
Hinterlegungsdatum: 22 Sep 2020 10:08
Letzte Änderung: 27 Feb 2023 11:25
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen