• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Reliable Age and Gender Estimation from Face Images: Stating the Confidence of Model Predictions
 
  • Details
  • Full
Options
2019
  • Konferenzbeitrag

Titel

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

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.
Author(s)
Terhörst, Philipp
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Huber, Marco
TU Darmstadt GRIS
Kolf, Jan Niklas
TU Darmstadt GRIS
Zelch, Ines
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Damer, Naser
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Kirchbuchner, Florian
Kuijper, Arjan
Hauptwerk
IEEE 10th International Conference on Biometrics Theory, Applications and Systems, BTAS 2019
Project(s)
CRISP
Funder
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Konferenz
International Conference on Biometrics - Theory, Applications and Systems (BTAS) 2019
Thumbnail Image
DOI
10.1109/BTAS46853.2019.9185975
Language
Englisch
google-scholar
IGD
Tags
  • CRISP

  • Lead Topic- Smart Cit...

  • Lead Topic- Visual Co...

  • Research Line- Comput...

  • Research Line- Human ...

  • Biometrics

  • Face recognition

  • Facial expression ana...

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022