Multi-scale Fully Convolutional Network for Face Detection in the Wild

Handle URI:
http://hdl.handle.net/10754/625996
Title:
Multi-scale Fully Convolutional Network for Face Detection in the Wild
Authors:
Bai, Yancheng; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
Face detection is a classical problem in computer vision. It is still a difficult task due to many nuisances that naturally occur in the wild. In this paper, we propose a multi-scale fully convolutional network for face detection. To reduce computation, the intermediate convolutional feature maps (conv) are shared by every scale model. We up-sample and down-sample the final conv map to approximate K levels of a feature pyramid, leading to a wide range of face scales that can be detected. At each feature pyramid level, a FCN is trained end-to-end to deal with faces in a small range of scale change. Because of the up-sampling, our method can detect very small faces (10×10 pixels). We test our MS-FCN detector on four public face detection datasets, including FDDB, WIDER FACE, AFW and PASCAL FACE. Extensive experiments show that it outperforms state-of-the-art methods. Also, MS-FCN runs at 23 FPS on a GPU for images of size 640×480 with no assumption on the minimum detectable face size.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program
Citation:
Bai Y, Ghanem B (2017) Multi-scale Fully Convolutional Network for Face Detection in the Wild. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Available: http://dx.doi.org/10.1109/CVPRW.2017.259.
Publisher:
IEEE
Journal:
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
KAUST Grant Number:
2016-KKI-2880
Conference/Event name:
30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Issue Date:
24-Aug-2017
DOI:
10.1109/CVPRW.2017.259
Type:
Conference Paper
Sponsors:
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research under grant 2016-KKI-2880.
Additional Links:
http://ieeexplore.ieee.org/document/8014993/
Appears in Collections:
Conference Papers; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorBai, Yanchengen
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2017-10-30T08:39:49Z-
dc.date.available2017-10-30T08:39:49Z-
dc.date.issued2017-08-24en
dc.identifier.citationBai Y, Ghanem B (2017) Multi-scale Fully Convolutional Network for Face Detection in the Wild. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Available: http://dx.doi.org/10.1109/CVPRW.2017.259.en
dc.identifier.doi10.1109/CVPRW.2017.259en
dc.identifier.urihttp://hdl.handle.net/10754/625996-
dc.description.abstractFace detection is a classical problem in computer vision. It is still a difficult task due to many nuisances that naturally occur in the wild. In this paper, we propose a multi-scale fully convolutional network for face detection. To reduce computation, the intermediate convolutional feature maps (conv) are shared by every scale model. We up-sample and down-sample the final conv map to approximate K levels of a feature pyramid, leading to a wide range of face scales that can be detected. At each feature pyramid level, a FCN is trained end-to-end to deal with faces in a small range of scale change. Because of the up-sampling, our method can detect very small faces (10×10 pixels). We test our MS-FCN detector on four public face detection datasets, including FDDB, WIDER FACE, AFW and PASCAL FACE. Extensive experiments show that it outperforms state-of-the-art methods. Also, MS-FCN runs at 23 FPS on a GPU for images of size 640×480 with no assumption on the minimum detectable face size.en
dc.description.sponsorshipThis work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research under grant 2016-KKI-2880.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/8014993/en
dc.titleMulti-scale Fully Convolutional Network for Face Detection in the Wilden
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.identifier.journal2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)en
dc.conference.date2017-07-21 to 2017-07-26en
dc.conference.name30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017en
dc.conference.locationHonolulu, HI, USAen
dc.contributor.institutionInstitute of Software, Chinese Academy of Science, Beijing, , , Chinaen
kaust.authorBai, Yanchengen
kaust.authorGhanem, Bernarden
kaust.grant.number2016-KKI-2880en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.