Show simple item record

dc.contributor.authorZhao, Y
dc.contributor.authorLiu, Y
dc.contributor.authorShen, C
dc.contributor.authorGao, Y
dc.contributor.authorXiong, S
dc.date.accessioned2019-12-06T03:22:02Z
dc.date.available2019-12-06T03:22:02Z
dc.date.issued2020
dc.identifier.issn0031-3203
dc.identifier.doi10.1016/j.patcog.2019.107114
dc.identifier.urihttp://hdl.handle.net/10072/389585
dc.description.abstractFacial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a large number of parameters, resulting in high memory cost. In this paper, we aim for a lightweight as well as effective solution to facial landmark detection. To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder. The proposed MobileFAN, with only 8% of the model size and lower computational cost, achieves superior or equivalent performance compared with state-of-the-art models. Moreover, by transferring the geometric structural information of a face graph from a large complex model to our proposed MobileFAN through feature-aligned distillation and feature-similarity distillation, the performance of MobileFAN is further improved in effectiveness and efficiency for face alignment. Extensive experiment results on three challenging facial landmark estimation benchmarks including COFW, 300W and WFLW show the superiority of our proposed MobileFAN against state-of-the-art methods.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherElsevier
dc.publisher.placeNetherlands
dc.relation.ispartofpagefrom107114: 1
dc.relation.ispartofpageto107114: 10
dc.relation.ispartofjournalPattern Recognition
dc.relation.ispartofvolume100
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchInformation Systems
dc.subject.fieldofresearchcode0906
dc.subject.fieldofresearchcode0801
dc.subject.fieldofresearchcode0806
dc.titleMobileFAN: Transferring deep hidden representation for face alignment
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationZhao, Y; Liu, Y; Shen, C; Gao, Y; Xiong, S, MobileFAN: Transferring deep hidden representation for face alignment, Pattern Recognition, 2020, 100, pp. 107114: 1-107114: 10
dcterms.licensehttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.date.updated2019-12-05T00:49:24Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2020 Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence, which permits unrestricted, non-commercial use, distribution and reproduction in any medium, providing that the work is properly cited.
gro.hasfulltextFull Text
gro.griffith.authorGao, Yongsheng
gro.griffith.authorZhao, Yang


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record