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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |