TY - GEN
T1 - Multi-scale Fully Convolutional Network for Face Detection in the Wild
AU - Bai, Yancheng
AU - Ghanem, Bernard
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/22
Y1 - 2017/8/22
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85030250936&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2017.259
DO - 10.1109/CVPRW.2017.259
M3 - Conference contribution
AN - SCOPUS:85030250936
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 2078
EP - 2087
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PB - IEEE Computer Society
T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Y2 - 21 July 2017 through 26 July 2017
ER -