• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Compact Models for Periocular Verification Through Knowledge Distillation
 
  • Details
  • Full
Options
2020
Conference Paper
Title

Compact Models for Periocular Verification Through Knowledge Distillation

Abstract
Despite the wide use of deep neural network for periocular verification, achieving smaller deep learning models with high performance that can be deployed on low computational powered devices remains a challenge. In term of computation cost, we present in this paper a lightweight deep learning model with only 1.1m of trainable parameters, DenseNet-20, based on DenseNet architecture. Further, we present an approach to enhance the verification performance of DenseNet-20 via knowledge distillation. With the experiments on VISPI dataset captured with two different smartphones, iPhone and Nokia, we show that introducing knowledge distillation to DenseNet-20 training phase outperforms the same model trained without knowledge distillation where the Equal Error Rate (EER) reduces from 8.36% to 4.56% EER on iPhone data, from 5.33% to 4.64% EER on Nokia data, and from 20.98% to 15.54% EER on cross-smartphone data.
Author(s)
Boutros, Fadi  orcid-logo
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Damer, Naser  
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Fang, Meiling  
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Raja, Kiran
NTNU, Gjovik, Norway
Kirchbuchner, Florian  orcid-logo
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Kuijper, Arjan  orcid-logo
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Mainwork
BIOSIG 2020, 19th International Conference of the Biometrics Special Interest Group. Proceedings  
Conference
Gesellschaft für Informatik, Special Interest Group on Biometrics and Electronic Signatures (BIOSIG International Conference) 2020  
Language
English
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Keyword(s)
  • Lead Topic: Smart City

  • Lead Topic: Visual Computing as a Service

  • Research Line: Computer vision (CV)

  • Research Line: Human computer interaction (HCI)

  • biometric

  • knowledge processing

  • deep learning

  • machine learning

  • CRISP

  • ATHENE

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024