With the rapid development of deep convolutional neural network, face detection has made great progress in recent years. WIDER FACE dataset, as a main benchmark, contributes greatly to this area. A large amount of methods have been put forward where PyramidBox designs an effective data augmentation strategy (Data-anchor-sampling) and context-based module for face detector. In this report, we improve each part to further boost the performance, including Balanced-data-anchor-sampling, Dual-PyramidAnchors and Dense Context Module. Specifically, Balanced-data-anchor-sampling obtains more uniform sampling of faces with different sizes. Dual-PyramidAnchors facilitate feature learning by introducing progressive anchor loss. Dense Context Module with dense connection not only enlarges receptive filed, but also passes information efficiently. Integrating these techniques, PyramidBox++ is constructed and achieves state-of-the-art performance in hard set.
@article{arxiv.1904.00386,
title = {PyramidBox++: High Performance Detector for Finding Tiny Face},
author = {Zhihang Li and Xu Tang and Junyu Han and Jingtuo Liu and Ran He},
journal= {arXiv preprint arXiv:1904.00386},
year = {2019}
}