English

Robust and High Performance Face Detector

Computer Vision and Pattern Recognition 2019-01-09 v1

Abstract

In recent years, face detection has experienced significant performance improvement with the boost of deep convolutional neural networks. In this report, we reimplement the state-of-the-art detector SRN and apply some tricks proposed in the recent literatures to obtain an extremely strong face detector, named VIM-FD. In specific, we exploit more powerful backbone network like DenseNet-121, revisit the data augmentation based on data-anchor-sampling proposed in PyramidBox, and use the max-in-out label and anchor matching strategy in SFD. In addition, we also introduce the attention mechanism to provide additional supervision. Over the most popular and challenging face detection benchmark, i.e., WIDER FACE, the proposed VIM-FD achieves state-of-the-art performance.

Keywords

Cite

@article{arxiv.1901.02350,
  title  = {Robust and High Performance Face Detector},
  author = {Yundong Zhang and Xiang Xu and Xiaotao Liu},
  journal= {arXiv preprint arXiv:1901.02350},
  year   = {2019}
}

Comments

arXiv admin note: text overlap with arXiv:1708.05237 and substantial text overlap with arXiv:1809.02693 by other authors

R2 v1 2026-06-23T07:06:06.729Z