Publication Type
Journal Article
Version
acceptedVersion
Publication Date
3-2020
Abstract
Recent years have witnessed promising results of exploring deep convolutional neural network for face detection. Despite making remarkable progress, face detection in the wild remains challenging especially when detecting faces at vastly different scales and characteristics. In this paper, we propose a novel simple yet effective framework of “Feature Agglomeration Networks” (FANet) to build a new single-stage face detector, which not only achieves state-of-the-art performance but also runs efficiently. As inspired by Feature Pyramid Networks (FPN) (Lin et al., 2017), the key idea of our framework is to exploit inherent multi-scale features of a single convolutional neural network by aggregating higher-level semantic feature maps of different scales as contextual cues to augment lower-level feature maps via a hierarchical agglomeration manner at marginal extra computation cost. We further propose a Hierarchical Loss to effectively train the FANet model. We evaluate the proposed FANet detector on several public face detection benchmarks, including PASCAL face, FDDB, and WIDER FACE datasets and achieved state-of-the-art results2. Our detector can run in real-time for VGA-resolution images on GPU.
Keywords
Hierarchical loss, Single-stage detectors, Context-aware, Feature agglomeration
Discipline
Databases and Information Systems | Data Storage Systems
Research Areas
Data Science and Engineering
Publication
Neurocomputing
Volume
380
First Page
180
Last Page
189
ISSN
0925-2312
Identifier
10.1016/j.neucom.2019.10.087
Publisher
Elsevier
Citation
ZHANG, Jialiang; WU, Xiongwei; HOI, Steven C. H.; and ZHU, Jianke.
Feature agglomeration networks for single stage face detection. (2020). Neurocomputing. 380, 180-189.
Available at: https://ink.library.smu.edu.sg/sis_research/5098
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1016/j.neucom.2019.10.087