GI LogoGI Logo
  • Login
Digital Library
    • All of DSpace

      • Communities & Collections
      • Titles
      • Authors
      • By Issue Date
      • Subjects
    • This Collection

      • Titles
      • Authors
      • By Issue Date
      • Subjects
Digital Library Gesellschaft für Informatik e.V.
GI-DL
    • English
    • Deutsch
  • English 
    • English
    • Deutsch
View Item 
  •   DSpace Home
  • Lecture Notes in Informatics
  • Proceedings
  • BIOSIG - Biometrics and Electronic Signatures
  • P282 - BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.
  •   DSpace Home
  • Lecture Notes in Informatics
  • Proceedings
  • BIOSIG - Biometrics and Electronic Signatures
  • P282 - BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group
  • View Item

Deep Domain Adaptation for Face Recognition using images captured from surveillance cameras

Author:
Banerjee, Samik [DBLP] ;
Bhattacharjee, Avishek [DBLP] ;
Das, Sukhendu [DBLP]
Abstract
Learning based on convolutional neural networks (CNNs) or deep learning has been a major research area with applications in face recognition (FR). However, performances of algorithms designed for FR are unsatisfactory when surveillance conditions severely degrade the test probes. The work presented in this paper has three contributions. First, it proposes a novel adaptive-CNN architecture of deep learning refurbished for domain adaptation (DA), to overcome the difference in feature distributions between the gallery and probe samples. The proposed architecture consists of three components: feature (FM), adaptive (AM) and classification (CM) modules. Secondly, a novel 2-stage algorithm for Mutually Exclusive Training (2-MET) based on stochastic gradient descent, has been proposed. The final stage of training in 2-MET freezes the layers of the FM and CM, while updating (tuning) only the parameters of the AM using a few probe (as target) samples. This helps the proposed deep-DA CNN to bridge the disparities in the distributions of the gallery and probe samples, resulting in enhanced domain-invariant representation for efficient deep-DA learning and classification. The third contribution comes from rigorous experimentations performed on three benchmark real-world surveillance face datasets with various kinds of degradations. This reveals the superior performance of the proposed adaptive-CNN architecture with 2-MET training, using Rank-1 recognition rates and ROC and CMC metrics, over many recent state-of-the-art techniques of CNN and DA.
  • Citation
  • BibTeX
Banerjee, S., Bhattacharjee, A. & Das, S., (2018). Deep Domain Adaptation for Face Recognition using images captured from surveillance cameras. In: Brömme, A., Busch, C., Dantcheva, A., Rathgeb, C. & Uhl, A. (Hrsg.), BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group. Bonn: Köllen Druck+Verlag GmbH.
@inproceedings{mci/Banerjee2018,
author = {Banerjee, Samik AND Bhattacharjee, Avishek AND Das, Sukhendu},
title = {Deep Domain Adaptation for Face Recognition using images captured from surveillance cameras},
booktitle = {BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group},
year = {2018},
editor = {Brömme, Arslan AND Busch, Christoph AND Dantcheva, Antitza AND Rathgeb, Christian AND Uhl, Andreas},
publisher = {Köllen Druck+Verlag GmbH},
address = {Bonn}
}
DateienGroesseFormatAnzeige
update_BIOSIG_2018_paper_5.pdf471.4Kb PDF View/Open

Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Send Feedback

More Info

ISBN: 978-3-88579-676-4
ISSN: 1617-5468
xmlui.MetaDataDisplay.field.date: 2018
Language: en (en)
Content Type: Text/Conference Paper

Keywords

  • Face Recognition
  • DA
  • Deep Learning
  • Low-Resolution
  • Denoising Auto-encoders.
Collections
  • P282 - BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group [32]

Show full item record


About uns | FAQ | Help | Imprint | Datenschutz

Gesellschaft für Informatik e.V. (GI), Kontakt: Geschäftsstelle der GI
Diese Digital Library basiert auf DSpace.

 

 


About uns | FAQ | Help | Imprint | Datenschutz

Gesellschaft für Informatik e.V. (GI), Kontakt: Geschäftsstelle der GI
Diese Digital Library basiert auf DSpace.