Local and Global Feature Aggregation-Aware Network for Salient Object Detection
With the rise of deep learning technology, salient object detection algorithms based on convolutional neural networks (CNNs) are gradually replacing traditional methods. The majority of existing studies, however, focused on the integration of multi-scale features, thereby ignoring the characteristic...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/2/231 |
_version_ | 1797494505730998272 |
---|---|
author | Zikai Da Yu Gao Zihan Xue Jing Cao Peizhen Wang |
author_facet | Zikai Da Yu Gao Zihan Xue Jing Cao Peizhen Wang |
author_sort | Zikai Da |
collection | DOAJ |
description | With the rise of deep learning technology, salient object detection algorithms based on convolutional neural networks (CNNs) are gradually replacing traditional methods. The majority of existing studies, however, focused on the integration of multi-scale features, thereby ignoring the characteristics of other significant features. To address this problem, we fully utilized the features to alleviate redundancy. In this paper, a novel CNN named local and global feature aggregation-aware network (LGFAN) has been proposed. It is a combination of the visual geometry group backbone for feature extraction, an attention module for high-quality feature filtering, and an aggregation module with a mechanism for rich salient features to ease the dilution process on the top-down pathway. Experimental results on five public datasets demonstrated that the proposed method improves computational efficiency while maintaining favorable performance. |
first_indexed | 2024-03-10T01:35:16Z |
format | Article |
id | doaj.art-2755af8291354797a195ffc660856c27 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T01:35:16Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-2755af8291354797a195ffc660856c272023-11-23T13:34:24ZengMDPI AGElectronics2079-92922022-01-0111223110.3390/electronics11020231Local and Global Feature Aggregation-Aware Network for Salient Object DetectionZikai Da0Yu Gao1Zihan Xue2Jing Cao3Peizhen Wang4School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan 243002, ChinaSchool of Business, Guilin University of Electronic Technology, Guilin 541000, ChinaSchool of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan 243002, ChinaSchool of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan 243002, ChinaKey Laboratory of Metallurgical Emission Reduction & Resources Recycling, Ministry of Education, Anhui University of Technology, Ma’anshan 243002, ChinaWith the rise of deep learning technology, salient object detection algorithms based on convolutional neural networks (CNNs) are gradually replacing traditional methods. The majority of existing studies, however, focused on the integration of multi-scale features, thereby ignoring the characteristics of other significant features. To address this problem, we fully utilized the features to alleviate redundancy. In this paper, a novel CNN named local and global feature aggregation-aware network (LGFAN) has been proposed. It is a combination of the visual geometry group backbone for feature extraction, an attention module for high-quality feature filtering, and an aggregation module with a mechanism for rich salient features to ease the dilution process on the top-down pathway. Experimental results on five public datasets demonstrated that the proposed method improves computational efficiency while maintaining favorable performance.https://www.mdpi.com/2079-9292/11/2/231salient object detectionCNNslocal and globalattentionaggregation |
spellingShingle | Zikai Da Yu Gao Zihan Xue Jing Cao Peizhen Wang Local and Global Feature Aggregation-Aware Network for Salient Object Detection Electronics salient object detection CNNs local and global attention aggregation |
title | Local and Global Feature Aggregation-Aware Network for Salient Object Detection |
title_full | Local and Global Feature Aggregation-Aware Network for Salient Object Detection |
title_fullStr | Local and Global Feature Aggregation-Aware Network for Salient Object Detection |
title_full_unstemmed | Local and Global Feature Aggregation-Aware Network for Salient Object Detection |
title_short | Local and Global Feature Aggregation-Aware Network for Salient Object Detection |
title_sort | local and global feature aggregation aware network for salient object detection |
topic | salient object detection CNNs local and global attention aggregation |
url | https://www.mdpi.com/2079-9292/11/2/231 |
work_keys_str_mv | AT zikaida localandglobalfeatureaggregationawarenetworkforsalientobjectdetection AT yugao localandglobalfeatureaggregationawarenetworkforsalientobjectdetection AT zihanxue localandglobalfeatureaggregationawarenetworkforsalientobjectdetection AT jingcao localandglobalfeatureaggregationawarenetworkforsalientobjectdetection AT peizhenwang localandglobalfeatureaggregationawarenetworkforsalientobjectdetection |