Foreground and Background Interaction Fusion Network for Camouflaged Object Detection
Aiming at the problem of incomplete detection results and blurred edge details in current camouflaged object detection (COD) methods, a novel Foreground and Background Interactive Fusion Network ( FBIFNet) was proposed to further improve the performance of COD through joint exploration of foreground...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin University of Science and Technology Publications
2025-04-01
|
| Series: | Journal of Harbin University of Science and Technology |
| Subjects: | |
| Online Access: | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2413 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849426476286345216 |
|---|---|
| author | WEI Mingjun LIU Ming LIU Yazhi LI Hui |
| author_facet | WEI Mingjun LIU Ming LIU Yazhi LI Hui |
| author_sort | WEI Mingjun |
| collection | DOAJ |
| description | Aiming at the problem of incomplete detection results and blurred edge details in current camouflaged object detection (COD) methods, a novel Foreground and Background Interactive Fusion Network ( FBIFNet) was proposed to further improve the performance of COD through joint exploration of foreground and background regions. FBIFNet contains a key Bilateral Interactive Fusion module (BIF), which uses a pair of complementary attentions to guide the network to jointly reason about camouflaged objects from both foreground and background directions and also utilizes an interaction strategy based on the bidirectional attention mechanism and a weighted fusion strategy to learn complementary information between foreground and background. In addition, an Attentional Cascaded Positioning module (ACP) is included, which can localize camouflaged objects from a global perspective and provide more accurate foreground and background guidance for BIF. With the two proposed modules, FBIFNet can more accurately detect camouflaged objects. Extensive experiments on three public datasets ( CAMO, COD10K, and NC4K) demonstrate that the proposed network outperforms state-of-the-art methods in related fields on four evaluation metrics. |
| format | Article |
| id | doaj-art-4f25e833a9574f7a98d53dd414f7ddca |
| institution | Kabale University |
| issn | 1007-2683 |
| language | zho |
| publishDate | 2025-04-01 |
| publisher | Harbin University of Science and Technology Publications |
| record_format | Article |
| series | Journal of Harbin University of Science and Technology |
| spelling | doaj-art-4f25e833a9574f7a98d53dd414f7ddca2025-08-20T03:29:23ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832025-04-013002536310.15938/j.jhust.2025.02.006Foreground and Background Interaction Fusion Network for Camouflaged Object DetectionWEI Mingjun0LIU Ming1LIU Yazhi2LI Hui3College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China; Hebei Key Laboratory of Industrial Intelligent Perception, Tangshan 063210, ChinaCollege of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China; Hebei Key Laboratory of Industrial Intelligent Perception, Tangshan 063210, China College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, ChinaAiming at the problem of incomplete detection results and blurred edge details in current camouflaged object detection (COD) methods, a novel Foreground and Background Interactive Fusion Network ( FBIFNet) was proposed to further improve the performance of COD through joint exploration of foreground and background regions. FBIFNet contains a key Bilateral Interactive Fusion module (BIF), which uses a pair of complementary attentions to guide the network to jointly reason about camouflaged objects from both foreground and background directions and also utilizes an interaction strategy based on the bidirectional attention mechanism and a weighted fusion strategy to learn complementary information between foreground and background. In addition, an Attentional Cascaded Positioning module (ACP) is included, which can localize camouflaged objects from a global perspective and provide more accurate foreground and background guidance for BIF. With the two proposed modules, FBIFNet can more accurately detect camouflaged objects. Extensive experiments on three public datasets ( CAMO, COD10K, and NC4K) demonstrate that the proposed network outperforms state-of-the-art methods in related fields on four evaluation metrics.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2413camouflaged object detectionforeground and background informationnon-local attentionfeature interactionfeature fusion |
| spellingShingle | WEI Mingjun LIU Ming LIU Yazhi LI Hui Foreground and Background Interaction Fusion Network for Camouflaged Object Detection Journal of Harbin University of Science and Technology camouflaged object detection foreground and background information non-local attention feature interaction feature fusion |
| title | Foreground and Background Interaction Fusion Network for Camouflaged Object Detection |
| title_full | Foreground and Background Interaction Fusion Network for Camouflaged Object Detection |
| title_fullStr | Foreground and Background Interaction Fusion Network for Camouflaged Object Detection |
| title_full_unstemmed | Foreground and Background Interaction Fusion Network for Camouflaged Object Detection |
| title_short | Foreground and Background Interaction Fusion Network for Camouflaged Object Detection |
| title_sort | foreground and background interaction fusion network for camouflaged object detection |
| topic | camouflaged object detection foreground and background information non-local attention feature interaction feature fusion |
| url | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2413 |
| work_keys_str_mv | AT weimingjun foregroundandbackgroundinteractionfusionnetworkforcamouflagedobjectdetection AT liuming foregroundandbackgroundinteractionfusionnetworkforcamouflagedobjectdetection AT liuyazhi foregroundandbackgroundinteractionfusionnetworkforcamouflagedobjectdetection AT lihui foregroundandbackgroundinteractionfusionnetworkforcamouflagedobjectdetection |