ADN for object detection
Owing to large‐scale diversity and location uncertainty in object detection, how to enrich semantic information has become an important issue that attracts a lot of concern. In this study, the authors propose a novel attentional detection network (ADN) to enrich semantic information of feature maps...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2020-03-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2018.5651 |
_version_ | 1797684790202204160 |
---|---|
author | Jinding Wang Haifeng Hu Xinlong Lu |
author_facet | Jinding Wang Haifeng Hu Xinlong Lu |
author_sort | Jinding Wang |
collection | DOAJ |
description | Owing to large‐scale diversity and location uncertainty in object detection, how to enrich semantic information has become an important issue that attracts a lot of concern. In this study, the authors propose a novel attentional detection network (ADN) to enrich semantic information of feature maps by adding an extra attention branch to the classic detection network. Compared to previous methods (e.g. feature pyramid network (FPN), single shot multibox detector (SSD)) that producing massive anchors in different layers of feature maps to detect objects with different scales and aspect ratios, which is very time‐consuming, their network is lightweight and do not need to produce extra anchors. Furthermore, ADN can be applied to different object detectors with little computational cost. Extensive experiments indicate that ADN has good detection performance on different datasets without bells and whistles. |
first_indexed | 2024-03-12T00:34:53Z |
format | Article |
id | doaj.art-23e03687794a4763930ba4f83d8ac902 |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-03-12T00:34:53Z |
publishDate | 2020-03-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-23e03687794a4763930ba4f83d8ac9022023-09-15T09:56:15ZengWileyIET Computer Vision1751-96321751-96402020-03-01142657210.1049/iet-cvi.2018.5651ADN for object detectionJinding Wang0Haifeng Hu1Xinlong Lu2School of Electronics and Information TechnologySun Yat‐sen UniversityWaihuan East Road, Higher Education Mega Centre, Panyu DistrictGuangzhouPeople's Republic of ChinaSchool of Electronics and Information TechnologySun Yat‐sen UniversityWaihuan East Road, Higher Education Mega Centre, Panyu DistrictGuangzhouPeople's Republic of ChinaSchool of Electronics and Information TechnologySun Yat‐sen UniversityWaihuan East Road, Higher Education Mega Centre, Panyu DistrictGuangzhouPeople's Republic of ChinaOwing to large‐scale diversity and location uncertainty in object detection, how to enrich semantic information has become an important issue that attracts a lot of concern. In this study, the authors propose a novel attentional detection network (ADN) to enrich semantic information of feature maps by adding an extra attention branch to the classic detection network. Compared to previous methods (e.g. feature pyramid network (FPN), single shot multibox detector (SSD)) that producing massive anchors in different layers of feature maps to detect objects with different scales and aspect ratios, which is very time‐consuming, their network is lightweight and do not need to produce extra anchors. Furthermore, ADN can be applied to different object detectors with little computational cost. Extensive experiments indicate that ADN has good detection performance on different datasets without bells and whistles.https://doi.org/10.1049/iet-cvi.2018.5651ADNobject detectionlarge-scale diversitylocation uncertaintysemantic informationattentional detection network |
spellingShingle | Jinding Wang Haifeng Hu Xinlong Lu ADN for object detection IET Computer Vision ADN object detection large-scale diversity location uncertainty semantic information attentional detection network |
title | ADN for object detection |
title_full | ADN for object detection |
title_fullStr | ADN for object detection |
title_full_unstemmed | ADN for object detection |
title_short | ADN for object detection |
title_sort | adn for object detection |
topic | ADN object detection large-scale diversity location uncertainty semantic information attentional detection network |
url | https://doi.org/10.1049/iet-cvi.2018.5651 |
work_keys_str_mv | AT jindingwang adnforobjectdetection AT haifenghu adnforobjectdetection AT xinlonglu adnforobjectdetection |