Logo des Repositoriums
 

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

Kurzanzeige
dc.contributor.authorBanerjee, Samik
dc.contributor.authorBhattacharjee, Avishek
dc.contributor.authorDas, Sukhendu
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.contributor.editorDantcheva, Antitza
dc.contributor.editorRathgeb, Christian
dc.contributor.editorUhl, Andreas
dc.date.accessioned2019-06-17T10:00:29Z
dc.date.available2019-06-17T10:00:29Z
dc.date.issued2018
dc.description.abstractLearning 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.en
dc.identifier.isbn978-3-88579-676-4
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/23811
dc.language.isoen
dc.publisherKöllen Druck+Verlag GmbH
dc.relation.ispartofBIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-283
dc.subjectFace Recognition
dc.subjectDA
dc.subjectDeep Learning
dc.subjectLow-Resolution
dc.subjectDenoising Auto-encoders.
dc.titleDeep Domain Adaptation for Face Recognition using images captured from surveillance camerasen
dc.typeText/Conference Paper
gi.citation.publisherPlaceBonn
gi.conference.date26.-28. September 2018
gi.conference.locationDarmstadt

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
update_BIOSIG_2018_paper_5.pdf
Größe:
471.49 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P282 - BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group