Feature agglomeration networks for single stage face detection

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 propos...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHANG, Jialiang, WU, Xiongwei, HOI, Steven C. H., ZHU, Jianke
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5098
https://ink.library.smu.edu.sg/context/sis_research/article/6101/viewcontent/1712.00721.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-6101
record_format dspace
spelling sg-smu-ink.sis_research-61012023-07-19T07:46:59Z Feature agglomeration networks for single stage face detection ZHANG, Jialiang WU, Xiongwei HOI, Steven C. H. ZHU, Jianke 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. 2020-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5098 info:doi/10.1016/j.neucom.2019.10.087 https://ink.library.smu.edu.sg/context/sis_research/article/6101/viewcontent/1712.00721.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Hierarchical loss Single-stage detectors Context-aware Feature agglomeration Databases and Information Systems Data Storage Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Hierarchical loss
Single-stage detectors
Context-aware
Feature agglomeration
Databases and Information Systems
Data Storage Systems
spellingShingle Hierarchical loss
Single-stage detectors
Context-aware
Feature agglomeration
Databases and Information Systems
Data Storage Systems
ZHANG, Jialiang
WU, Xiongwei
HOI, Steven C. H.
ZHU, Jianke
Feature agglomeration networks for single stage face detection
description 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.
format text
author ZHANG, Jialiang
WU, Xiongwei
HOI, Steven C. H.
ZHU, Jianke
author_facet ZHANG, Jialiang
WU, Xiongwei
HOI, Steven C. H.
ZHU, Jianke
author_sort ZHANG, Jialiang
title Feature agglomeration networks for single stage face detection
title_short Feature agglomeration networks for single stage face detection
title_full Feature agglomeration networks for single stage face detection
title_fullStr Feature agglomeration networks for single stage face detection
title_full_unstemmed Feature agglomeration networks for single stage face detection
title_sort feature agglomeration networks for single stage face detection
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/5098
https://ink.library.smu.edu.sg/context/sis_research/article/6101/viewcontent/1712.00721.pdf
_version_ 1772829244151300096