학술논문
SSFD+: A Robust Two-Stage Face Detector
Document Type
Periodical
Author
Source
IEEE Transactions on Biometrics, Behavior, and Identity Science IEEE Trans. Biom. Behav. Identity Sci. Biometrics, Behavior, and Identity Science, IEEE Transactions on. 1(3):181-191 Jul, 2019
Subject
Language
ISSN
2637-6407
Abstract
Face detectors based on deep learning have demonstrated great progress in detecting multi-scale faces by using multi-scale feature maps and input pyramids. However, using input pyramids and multi-scale feature maps increases the training difficulty and complexity of the network. In this paper, we focus on achieving comparable performance and simplifying the network architecture for detecting multi-scale faces. To enable network learning of multi-scale facial features from a single-scale feature map and a single-scale input image: 1) we conducted a comparative study to investigate which layer contributes more to detecting multi-scale faces and 2) we designed and implemented a simple network structure to improve the performance of detecting multi-scale faces by incorporating additional contextual information. SSFD + achieves mAPs of (91.3%, 90.3%, 83.1%) and (92.4%, 90.9%, 83.7%) on the (easy, medium, and hard) subsets of the WIDER FACE validation and testing datasets, respectively, and promising results on the FDDB, PASCAL Faces, and AFW datasets.