Salient object detection with non-local feature enhancement and edge reconstruction

Abstract The salient object detection task based on deep learning has made significant advances. However, the existing methods struggle to capture long-range dependencies and edge information in complex images, which hinders precise prediction of salient objects. To this end, we propose a salient ob...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Xu, Jingyao Jiang, Lei Cai, Haojie Chai, Hanjun Ma
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-84680-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850048835688071168
author Tao Xu
Jingyao Jiang
Lei Cai
Haojie Chai
Hanjun Ma
author_facet Tao Xu
Jingyao Jiang
Lei Cai
Haojie Chai
Hanjun Ma
author_sort Tao Xu
collection DOAJ
description Abstract The salient object detection task based on deep learning has made significant advances. However, the existing methods struggle to capture long-range dependencies and edge information in complex images, which hinders precise prediction of salient objects. To this end, we propose a salient object detection method with non-local feature enhancement and edge reconstruction. Firstly, we adopt self-attention mechanisms to capture long-range dependencies. The non-local feature enhancement module uses non-local operation and graph convolution to model and reason the region-wise relations, which enables to capture high-order semantic information. Secondly, we design an edge reconstruction module to capture essential edge information. It aggregates various image details from different branches to better capture and enhance edge information, thereby generating saliency maps with more exact edges. Extensive experiments on six widely used benchmarks show that the proposed method achieves competitive results, with an average of Structure-Measure and Enhanced-alignment Measure values of 0.890 and 0.931, respectively.
format Article
id doaj-art-d01dcfe3eba148888efa33b38e6de3af
institution DOAJ
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d01dcfe3eba148888efa33b38e6de3af2025-08-20T02:53:51ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-024-84680-xSalient object detection with non-local feature enhancement and edge reconstructionTao Xu0Jingyao Jiang1Lei Cai2Haojie Chai3Hanjun Ma4School of Artificial Intelligence, Henan Institute of Science and TechnologySchool of Mechanical and Electrical Engineering, Henan Institute of Science and TechnologySchool of Artificial Intelligence, Henan Institute of Science and TechnologySchool of Artificial Intelligence, Henan Institute of Science and TechnologySchool of Food Science, Henan Institute of Science and TechnologyAbstract The salient object detection task based on deep learning has made significant advances. However, the existing methods struggle to capture long-range dependencies and edge information in complex images, which hinders precise prediction of salient objects. To this end, we propose a salient object detection method with non-local feature enhancement and edge reconstruction. Firstly, we adopt self-attention mechanisms to capture long-range dependencies. The non-local feature enhancement module uses non-local operation and graph convolution to model and reason the region-wise relations, which enables to capture high-order semantic information. Secondly, we design an edge reconstruction module to capture essential edge information. It aggregates various image details from different branches to better capture and enhance edge information, thereby generating saliency maps with more exact edges. Extensive experiments on six widely used benchmarks show that the proposed method achieves competitive results, with an average of Structure-Measure and Enhanced-alignment Measure values of 0.890 and 0.931, respectively.https://doi.org/10.1038/s41598-024-84680-x
spellingShingle Tao Xu
Jingyao Jiang
Lei Cai
Haojie Chai
Hanjun Ma
Salient object detection with non-local feature enhancement and edge reconstruction
Scientific Reports
title Salient object detection with non-local feature enhancement and edge reconstruction
title_full Salient object detection with non-local feature enhancement and edge reconstruction
title_fullStr Salient object detection with non-local feature enhancement and edge reconstruction
title_full_unstemmed Salient object detection with non-local feature enhancement and edge reconstruction
title_short Salient object detection with non-local feature enhancement and edge reconstruction
title_sort salient object detection with non local feature enhancement and edge reconstruction
url https://doi.org/10.1038/s41598-024-84680-x
work_keys_str_mv AT taoxu salientobjectdetectionwithnonlocalfeatureenhancementandedgereconstruction
AT jingyaojiang salientobjectdetectionwithnonlocalfeatureenhancementandedgereconstruction
AT leicai salientobjectdetectionwithnonlocalfeatureenhancementandedgereconstruction
AT haojiechai salientobjectdetectionwithnonlocalfeatureenhancementandedgereconstruction
AT hanjunma salientobjectdetectionwithnonlocalfeatureenhancementandedgereconstruction