Hourglass Face Detector for Hard Face

Zijun Yu, Jian Yin, Qiang Zhang, Wenming Yang, Jing-Hao Xue, Qingmin Liao

Abstract

Face detection is an upstream task of facial image analysis. In many real-world scenarios, we need to detect small, occluded or dense faces that are hard to detect, but hard face detection is a challenging task in particular considering the balance between accuracy and inference speed for real-world applications. This paper proposes an Hourglass Face Detector (HFD) for hard face by developing a deep one-stage fully-convolutional hourglass network, which achieves an excellent balance between accuracy and inference speed. To this end, the HFD firstly shrinks a feature map by a series of stridden convolutional layers rather than pooling layers, so that useful subtle information is preserved better. Secondly, it exploits context information by merging fine-grained shallow feature maps with deep ones full of semantic information, making a better fusion of detailed information and semantic information to achieve a better detection of small faces. Moreover, the HFD exploits prior and multiscale information from the training data to enhance its scale-invariance and adaptability of anchor scales. Compared with the SSH and S3FD methods, the HFD can achieve a better performance in average precision on detecting hard faces as well as a quicker inference. Experiments on the WIDER FACE and FDDB datasets demonstrate the superior performance of our proposed method.
BibTeX
@inproceedings{yu2021hourglass,
  author = {Zijun Yu and Jian Yin and Qiang Zhang and Wenming Yang and Jing-Hao Xue and Qingmin Liao},
  title = {{Hourglass Face Detector for Hard Face}},
  booktitle = {IJCNN},
  year = {2021},
  doi = {10.1109/ijcnn52387.2021.9533674},
}

Loading related content...

Figure