In this paper, we propose a novel Automatic and Scalable Face Detector (ASFD), which is based on a combination of neural architecture search techniques as well as a new loss design. First, we propose an automatic feature enhance module named Auto-FEM by improved differential architecture search, which allows efficient multi-scale feature fusion and context enhancement. Second, we use Distance-based Regression and Margin-based Classification (DRMC) multi-task loss to predict accurate bounding boxes and learn highly discriminative deep features. Third, we adopt compound scaling methods and uniformly scale the backbone, feature modules, and head networks to develop a family of ASFD, which are consistently more efficient than the state-of-the-art face detectors. Extensive experiments conducted on popular benchmarks, e.g. WIDER FACE and FDDB, demonstrate that our ASFD-D6 outperforms the prior strong competitors, and our lightweight ASFD-D0 runs at more than 120 FPS with Mobilenet for VGA-resolution images.
@article{arxiv.2003.11228,
title = {ASFD: Automatic and Scalable Face Detector},
author = {Bin Zhang and Jian Li and Yabiao Wang and Ying Tai and Chengjie Wang and Jilin Li and Feiyue Huang and Yili Xia and Wenjiang Pei and Rongrong Ji},
journal= {arXiv preprint arXiv:2003.11228},
year = {2020}
}
Comments
Ranked No.1 on WIDER Face (http://shuoyang1213.me/WIDERFACE/WiderFace_Results.html)