Multi-Task Learning Using Task Dependencies for Face Attributes Prediction

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 37
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorFan, Diko
dc.contributor.authorKim, Hyunwooko
dc.contributor.authorKim, Junmoko
dc.contributor.authorLiu, Yunhuiko
dc.contributor.authorHuang, Qiangko
dc.date.accessioned2019-07-23T06:21:19Z-
dc.date.available2019-07-23T06:21:19Z-
dc.date.created2019-07-23-
dc.date.issued2019-06-
dc.identifier.citationAPPLIED SCIENCES-BASEL, v.9, no.12-
dc.identifier.issn2076-3417-
dc.identifier.urihttp://hdl.handle.net/10203/263748-
dc.description.abstractFace attributes prediction has an increasing amount of applications in human-computer interaction, face verification and video surveillance. Various studies show that dependencies exist in face attributes. Multi-task learning architecture can build a synergy among the correlated tasks by parameter sharing in the shared layers. However, the dependencies between the tasks have been ignored in the task-specific layers of most multi-task learning architectures. Thus, how to further boost the performance of individual tasks by using task dependencies among face attributes is quite challenging. In this paper, we propose a multi-task learning using task dependencies architecture for face attributes prediction and evaluate the performance with the tasks of smile and gender prediction. The designed attention modules in task-specific layers of our proposed architecture are used for learning task-dependent disentangled representations. The experimental results demonstrate the effectiveness of our proposed network by comparing with the traditional multi-task learning architecture and the state-of-the-art methods on Faces of the world (FotW) and Labeled faces in the wild-a (LFWA) datasets.-
dc.languageEnglish-
dc.publisherMDPI-
dc.titleMulti-Task Learning Using Task Dependencies for Face Attributes Prediction-
dc.typeArticle-
dc.identifier.wosid000473754800144-
dc.identifier.scopusid2-s2.0-85068149943-
dc.type.rimsART-
dc.citation.volume9-
dc.citation.issue12-
dc.citation.publicationnameAPPLIED SCIENCES-BASEL-
dc.identifier.doi10.3390/app9122535-
dc.contributor.localauthorKim, Junmo-
dc.contributor.nonIdAuthorFan, Di-
dc.contributor.nonIdAuthorKim, Hyunwoo-
dc.contributor.nonIdAuthorLiu, Yunhui-
dc.contributor.nonIdAuthorHuang, Qiang-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthormulti-task learning-
dc.subject.keywordAuthortask dependencies-
dc.subject.keywordAuthorattention-
dc.subject.keywordAuthorface attributes prediction-
dc.subject.keywordAuthordeep convolutional neural network-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0