Multi-scale Fully Convolutional Network for Face Detection in the Wild
Type
Conference PaperAuthors
Bai, YanchengGhanem, Bernard

KAUST Department
Visual Computing Center (VCC)Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
KAUST Grant Number
2016-KKI-2880Date
2017-08-24Online Publication Date
2017-08-24Print Publication Date
2017-07Permanent link to this record
http://hdl.handle.net/10754/625996
Metadata
Show full item recordAbstract
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.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.Sponsors
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research under grant 2016-KKI-2880.Conference/Event name
30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017Additional Links
http://ieeexplore.ieee.org/document/8014993/ae974a485f413a2113503eed53cd6c53
10.1109/CVPRW.2017.259