Full metadata record
DC FieldValueLanguage
dc.contributor.authorOrganisciak, Daniel
dc.contributor.authorRiachy, Chirine
dc.contributor.authorAslam, Nauman
dc.contributor.authorShum, Hubert P. H.
dc.contributor.editorSkala, Václav
dc.date.accessioned2019-10-22T07:12:04Z
dc.date.available2019-10-22T07:12:04Z
dc.date.issued2019
dc.identifier.citationJournal of WSCG. 2019, vol. 27, no. 2, p. 161-169.en
dc.identifier.issn1213-6980 (CD-ROM)
dc.identifier.issn1213-6972 (print)
dc.identifier.issn1213-6964 (on-line)
dc.identifier.urihttp://hdl.handle.net/11025/35600
dc.format9 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.rights© Václav Skala - UNION Agencycs
dc.subjectopakovaná identifikace osobycs
dc.subjectsqueeze and excitationcs
dc.subjecttrojnásobná ztrátacs
dc.subjectmetrické učenícs
dc.subjectsiamská síťcs
dc.subjecteuklidycs
dc.subjectpozornost kanálucs
dc.titleTriplet Loss with Channel Attention for Person Re-identificationen
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThe triplet loss function has seen extensive use within person re-identification. Most works focus on either improving the mining algorithm or adding new terms to the loss function itself. Our work instead concentrates on two other core components of the triplet loss that have been under-researched. First, we improve the standard Euclidean distance with dynamic weights, which are selected based on the standard deviation of features across the batch. Second, we exploit channel attention via a squeeze and excitation unit in the backbone model to emphasise important features throughout all layers of the model. This ensures that the output feature vector is a better representation of the image, and is also more suitable to use within our dynamically weighted Euclidean distance function. We demonstrate that our alterations provide significant performance improvement across popular reidentification data sets, including almost 10% mAP improvement on the CUHK03 data set. The proposed model attains results competitive with many state-of-the-art person re-identification models.en
dc.subject.translatedperson re-identificationen
dc.subject.translatedsqueeze and excitationen
dc.subject.translatedtriplet lossen
dc.subject.translatedmetric learningen
dc.subject.translatedsiamese networken
dc.subject.translatedweighted Euclideanen
dc.subject.translatedchannel attentionen
dc.identifier.doihttps://doi.org/10.24132/JWSCG.2019.27.2.9
dc.type.statusPeer-revieweden
Appears in Collections:Volume 27, Number 2 (2019)

Files in This Item:
File Description SizeFormat 
Organisciak.pdfPlný text897,6 kBAdobe PDFView/Open
Show simple item record


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/35600

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

search
navigation
  1. DSpace at University of West Bohemia
  2. Publikace ZČU / UWB Publications
  3. Časopisy ZČU / UWB Journals
  4. Journal of WSCG
  5. Volume 27 (2019)
  6. Volume 27, Number 2 (2019)