CGDINet: A Deep Learning-Based Salient Object Detection Algorithm
Salient object detection (SOD) is a key preprocessing step in computer vision, widely used in object tracking, action recognition, and image retrieval, among other fields. However, traditional SOD algorithms often face issues such as rough object boundaries, incomplete extraction of global image fea...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820319/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542525308895232 |
|---|---|
| author | Chengyu Hu Jianxin Guo Hanfei Xie Qing Zhu Baoxi Yuan Yujie Gao Xiangyang Ma Jialu Chen Juan Tian |
| author_facet | Chengyu Hu Jianxin Guo Hanfei Xie Qing Zhu Baoxi Yuan Yujie Gao Xiangyang Ma Jialu Chen Juan Tian |
| author_sort | Chengyu Hu |
| collection | DOAJ |
| description | Salient object detection (SOD) is a key preprocessing step in computer vision, widely used in object tracking, action recognition, and image retrieval, among other fields. However, traditional SOD algorithms often face issues such as rough object boundaries, incomplete extraction of global image features, and insufficient attention to key areas. To address these problems, an improved significance object detection network—CGDINet (Coordinate Attention-Group Consensus Aggregation Module-Depth Auxiliary Module-Inverse Saliency Pyramid Reconstruction Network)—is proposed. CGDINet introduces the Group Consensus Aggregation Module (GCAM) embedded with the Coordinate Attention (CA) mechanism, named CAGM (Coordinate Attention-Group Consensus Aggregation Module), to enhance global feature capture capabilities and improve the processing of directional features. Additionally, the Depth Auxiliary Module (DAM) is incorporated to enhance the focus on important regions. Experiments were conducted on five public datasets (DUT-OMRON, ECSSD, PASCAL-S, DUTS-TE, and HKU-IS). The results show that CGDINet outperforms other mainstream significance object detection models in evaluation metrics such as <inline-formula> <tex-math notation="LaTeX">${\mathrm {maxF}}_{\mathrm {\beta }}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\mathrm {S}_{\mathrm {\alpha }}$ </tex-math></inline-formula>, and MAE, with almost no increase in computational cost (FLOPs) and parameters. The experimental results validate that CGDINet can effectively address the issues of incomplete global feature extraction and insufficient attention to key areas, thereby significantly enhancing the performance of significance object detection. |
| format | Article |
| id | doaj-art-17c677a409494e6f8d98f69333cb478a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-17c677a409494e6f8d98f69333cb478a2025-01-14T00:02:28ZengIEEEIEEE Access2169-35362025-01-01134697472310.1109/ACCESS.2024.352530310820319CGDINet: A Deep Learning-Based Salient Object Detection AlgorithmChengyu Hu0https://orcid.org/0009-0004-6838-2428Jianxin Guo1https://orcid.org/0000-0003-0490-7649Hanfei Xie2https://orcid.org/0009-0000-7252-4039Qing Zhu3Baoxi Yuan4https://orcid.org/0000-0002-5220-879XYujie Gao5Xiangyang Ma6https://orcid.org/0009-0006-2767-6424Jialu Chen7Juan Tian8https://orcid.org/0009-0004-4478-1758School of Electronic Information, Xijing University, Xi’an, ChinaSchool of Electronic Information, Xijing University, Xi’an, ChinaSchool of Electronic Information, Xijing University, Xi’an, ChinaBeijing Hengyue Intelligent Information Technology Company Ltd., Xi’an, ChinaSchool of Electronic Information, Xijing University, Xi’an, ChinaSchool of Electronic Information, Xijing University, Xi’an, ChinaSchool of Electronic Information, Xijing University, Xi’an, ChinaSchool of Electronic Information, Xijing University, Xi’an, ChinaSchool of Humanities and Education, Xijing University, Xi’an, ChinaSalient object detection (SOD) is a key preprocessing step in computer vision, widely used in object tracking, action recognition, and image retrieval, among other fields. However, traditional SOD algorithms often face issues such as rough object boundaries, incomplete extraction of global image features, and insufficient attention to key areas. To address these problems, an improved significance object detection network—CGDINet (Coordinate Attention-Group Consensus Aggregation Module-Depth Auxiliary Module-Inverse Saliency Pyramid Reconstruction Network)—is proposed. CGDINet introduces the Group Consensus Aggregation Module (GCAM) embedded with the Coordinate Attention (CA) mechanism, named CAGM (Coordinate Attention-Group Consensus Aggregation Module), to enhance global feature capture capabilities and improve the processing of directional features. Additionally, the Depth Auxiliary Module (DAM) is incorporated to enhance the focus on important regions. Experiments were conducted on five public datasets (DUT-OMRON, ECSSD, PASCAL-S, DUTS-TE, and HKU-IS). The results show that CGDINet outperforms other mainstream significance object detection models in evaluation metrics such as <inline-formula> <tex-math notation="LaTeX">${\mathrm {maxF}}_{\mathrm {\beta }}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\mathrm {S}_{\mathrm {\alpha }}$ </tex-math></inline-formula>, and MAE, with almost no increase in computational cost (FLOPs) and parameters. The experimental results validate that CGDINet can effectively address the issues of incomplete global feature extraction and insufficient attention to key areas, thereby significantly enhancing the performance of significance object detection.https://ieeexplore.ieee.org/document/10820319/Salient object detectiondeep learningInSPyReNetCAGMDAM |
| spellingShingle | Chengyu Hu Jianxin Guo Hanfei Xie Qing Zhu Baoxi Yuan Yujie Gao Xiangyang Ma Jialu Chen Juan Tian CGDINet: A Deep Learning-Based Salient Object Detection Algorithm IEEE Access Salient object detection deep learning InSPyReNet CAGM DAM |
| title | CGDINet: A Deep Learning-Based Salient Object Detection Algorithm |
| title_full | CGDINet: A Deep Learning-Based Salient Object Detection Algorithm |
| title_fullStr | CGDINet: A Deep Learning-Based Salient Object Detection Algorithm |
| title_full_unstemmed | CGDINet: A Deep Learning-Based Salient Object Detection Algorithm |
| title_short | CGDINet: A Deep Learning-Based Salient Object Detection Algorithm |
| title_sort | cgdinet a deep learning based salient object detection algorithm |
| topic | Salient object detection deep learning InSPyReNet CAGM DAM |
| url | https://ieeexplore.ieee.org/document/10820319/ |
| work_keys_str_mv | AT chengyuhu cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT jianxinguo cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT hanfeixie cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT qingzhu cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT baoxiyuan cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT yujiegao cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT xiangyangma cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT jialuchen cgdinetadeeplearningbasedsalientobjectdetectionalgorithm AT juantian cgdinetadeeplearningbasedsalientobjectdetectionalgorithm |