Multi-Scale Fully Convolutional Network for Fast Face Detection

Yancheng Bai, Wenjing Ma, Yucheng Li, Liangliang Cao, Wen Guo and Luwei Yang

Abstract

Image pyramid is a common strategy in detecting objects with different scales in an image. The computation of features at every scale of a finely-sampled image pyramid is the computational bottleneck of many modern face detectors. To deal with this problem, we propose a multi-scale fully convolutional network framework for face detection. In our detector, face models at different scales are trained end-to-end and they share the same convolutional feature maps. During testing, only images at octave-spaced scale intervals need to be processed by our detector. And faces of different scales between two consecutive octaves can be detected by multi-scale models in our system. This makes our detector very efficient and can run about 100 FPS on a GPU for VGA images. Meanwhile, our detector shows superior performance over most of state-of-the-art ones on three challenging benchmarks, including FDDB, AFW, and PASCAL faces.

Session

Posters 1

Files

Extended Abstract (PDF, 839K)
Paper (PDF, 3M)

DOI

10.5244/C.30.51
https://dx.doi.org/10.5244/C.30.51

Citation

Bibtex

        @inproceedings{BMVC2016_51,
        	title={Multi-Scale Fully Convolutional Network for Fast Face Detection},
        	author={Yancheng Bai, Wenjing Ma, Yucheng Li, Liangliang Cao, Wen Guo and Luwei Yang},
        	year={2016},
        	month={September},
        	pages={51.1-51.12},
        	articleno={51},
        	numpages={12},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.51},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.51}
        }