ASFD: Automatic and Scalable Face Detector
This work addresses the need for efficient and accurate face detectors in computer vision applications, representing an incremental improvement through hybrid methods.
The paper tackles the problem of face detection by proposing an Automatic and Scalable Face Detector (ASFD) that combines neural architecture search and a new loss design, resulting in models that outperform prior competitors on benchmarks like WIDER FACE and FDDB, with a lightweight version running at over 120 FPS for VGA-resolution images.
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.