EFCRFNet: A novel multi-scale framework for salient object detection.
Salient Object Detection (SOD) is a fundamental task in computer vision, aiming to identify prominent regions within images. Traditional methods and deep learning-based models often encounter challenges in capturing crucial information in complex scenes, particularly due to inadequate edge feature e...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0323757 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849731750539821056 |
|---|---|
| author | Hong Peng Yunfei Hu Baocai Yu Zhen Zhang |
| author_facet | Hong Peng Yunfei Hu Baocai Yu Zhen Zhang |
| author_sort | Hong Peng |
| collection | DOAJ |
| description | Salient Object Detection (SOD) is a fundamental task in computer vision, aiming to identify prominent regions within images. Traditional methods and deep learning-based models often encounter challenges in capturing crucial information in complex scenes, particularly due to inadequate edge feature extraction, which compromises the precise delineation of object contours and boundaries. To address these challenges, we introduce EFCRFNet, a novel multi-scale feature extraction model that incorporates two innovative modules: the Enhanced Conditional Random Field (ECRF) and the Edge Feature Enhancement Module (EFEM). The ECRF module leverages advanced spatial attention mechanisms to enhance multimodal feature fusion, enabling robust detection in complex environments. Concurrently, the EFEM module focuses on refining edge features to strengthen multi-scale feature representation, significantly improving boundary recognition accuracy. Extensive experiments on standard benchmark datasets demonstrate that EFCRFNet achieves notable performance gains across key evaluation metrics, including MAE (0.64%), Fm (1.04%), Em (8.73%), and Sm (7.4%). These results underscore the effectiveness of EFCRFNet in enhancing detection accuracy and optimizing feature fusion, advancing the state of the art in salient object detection. |
| format | Article |
| id | doaj-art-6d4c5a7e3ff642f48d64198e1b4282db |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-6d4c5a7e3ff642f48d64198e1b4282db2025-08-20T03:08:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032375710.1371/journal.pone.0323757EFCRFNet: A novel multi-scale framework for salient object detection.Hong PengYunfei HuBaocai YuZhen ZhangSalient Object Detection (SOD) is a fundamental task in computer vision, aiming to identify prominent regions within images. Traditional methods and deep learning-based models often encounter challenges in capturing crucial information in complex scenes, particularly due to inadequate edge feature extraction, which compromises the precise delineation of object contours and boundaries. To address these challenges, we introduce EFCRFNet, a novel multi-scale feature extraction model that incorporates two innovative modules: the Enhanced Conditional Random Field (ECRF) and the Edge Feature Enhancement Module (EFEM). The ECRF module leverages advanced spatial attention mechanisms to enhance multimodal feature fusion, enabling robust detection in complex environments. Concurrently, the EFEM module focuses on refining edge features to strengthen multi-scale feature representation, significantly improving boundary recognition accuracy. Extensive experiments on standard benchmark datasets demonstrate that EFCRFNet achieves notable performance gains across key evaluation metrics, including MAE (0.64%), Fm (1.04%), Em (8.73%), and Sm (7.4%). These results underscore the effectiveness of EFCRFNet in enhancing detection accuracy and optimizing feature fusion, advancing the state of the art in salient object detection.https://doi.org/10.1371/journal.pone.0323757 |
| spellingShingle | Hong Peng Yunfei Hu Baocai Yu Zhen Zhang EFCRFNet: A novel multi-scale framework for salient object detection. PLoS ONE |
| title | EFCRFNet: A novel multi-scale framework for salient object detection. |
| title_full | EFCRFNet: A novel multi-scale framework for salient object detection. |
| title_fullStr | EFCRFNet: A novel multi-scale framework for salient object detection. |
| title_full_unstemmed | EFCRFNet: A novel multi-scale framework for salient object detection. |
| title_short | EFCRFNet: A novel multi-scale framework for salient object detection. |
| title_sort | efcrfnet a novel multi scale framework for salient object detection |
| url | https://doi.org/10.1371/journal.pone.0323757 |
| work_keys_str_mv | AT hongpeng efcrfnetanovelmultiscaleframeworkforsalientobjectdetection AT yunfeihu efcrfnetanovelmultiscaleframeworkforsalientobjectdetection AT baocaiyu efcrfnetanovelmultiscaleframeworkforsalientobjectdetection AT zhenzhang efcrfnetanovelmultiscaleframeworkforsalientobjectdetection |