Faster R-CNN is one of the most representative and successful methods for object detection, and has been becoming increasingly popular in various objection detection applications. In this report, we propose a robust deep face detection approach based on Faster R-CNN. In our approach, we exploit several new techniques including new multi-task loss function design, online hard example mining, and multi-scale training strategy to improve Faster R-CNN in multiple aspects. The proposed approach is well suited for face detection, so we call it Face R-CNN. Extensive experiments are conducted on two most popular and challenging face detection benchmarks, FDDB and WIDER FACE, to demonstrate the superiority of the proposed approach over state-of-the-arts.
@article{arxiv.1706.01061,
title = {Face R-CNN},
author = {Hao Wang and Zhifeng Li and Xing Ji and Yitong Wang},
journal= {arXiv preprint arXiv:1706.01061},
year = {2017}
}