How transferable are CNN-based features for age and gender classification?

Gökhan Özbulak, Yusuf Aytar, Hazim Kemal Ekenel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

80 Citations (Scopus)

Abstract

Age and gender are complementary soft biometric traits for face recognition. Successful estimation of age and gender from facial images taken under real-world conditions can contribute improving the identification results in the wild. In this study, in order to achieve robust age and gender classification in the wild, we have benefited from Deep Convolutional Neural Networks based representation. We have explored transferability of existing deep convolutional neural network (CNN) models for age and gender classification. The generic AlexNet-like architecture and domain specific VGG-Face CNN model are employed and fine-tuned with the Adience dataset prepared for age and gender classification in uncontrolled environments. In addition, task specific GilNet CNN model has also been utilized and used as a baseline method in order to compare with transferred models. Experimental results show that both transferred deep CNN models outperform the GilNet CNN model, which is the state-of-the-art age and gender classification approach on the Adience dataset, by an absolute increase of 7% and 4.5% in accuracy, respectively. This outcome indicates that transferring a deep CNN model can provide better classification performance than a task specific CNN model, which has a limited number of layers and trained from scratch using a limited amount of data as in the case of GilNet. Domain specific VGG-Face CNN model has been found to be more useful and provided better performance for both age and gender classification tasks, when compared with generic AlexNet-like model, which shows that transfering from a closer domain is more useful.

Original languageEnglish
Title of host publicationProceedings of the 15th International Conference of the Biometrics Special Interest Group, BIOSIG 2016
EditorsChristoph Busch, Andreas Uhl, Arslan Bromme, Christian Rathgeb
PublisherGesellschaft fur Informatik (GI)
ISBN (Electronic)9783885796541
DOIs
Publication statusPublished - 4 Nov 2016
Event15th International Conference of the Biometrics Special Interest Group, BIOSIG 2016 - Darmstadt, Germany
Duration: 21 Sept 201623 Sept 2016

Publication series

NameLecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)
VolumeP-260
ISSN (Print)1617-5468

Conference

Conference15th International Conference of the Biometrics Special Interest Group, BIOSIG 2016
Country/TerritoryGermany
CityDarmstadt
Period21/09/1623/09/16

Bibliographical note

Publisher Copyright:
© 2016 Gesellschaft für Informatik e.V., Bonn, Germany.

Keywords

  • Age classification
  • Convolutional Neural Networks
  • Deep learning
  • Gender classification
  • Soft biometrics
  • Transfer learning

Fingerprint

Dive into the research topics of 'How transferable are CNN-based features for age and gender classification?'. Together they form a unique fingerprint.

Cite this