Learning Dynamic Structural Specialization for Underwater Salient Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916015397404672 |
|---|---|
| author | Hong, Lin Wang, Chenhui Deng, Linan Cui, Yuning Zhang, Yu Wang, Xin Zhang, Bojian Ren, Wenqi Yang, Xingchen Zhang, Fumin |
| author_facet | Hong, Lin Wang, Chenhui Deng, Linan Cui, Yuning Zhang, Yu Wang, Xin Zhang, Bojian Ren, Wenqi Yang, Xingchen Zhang, Fumin |
| contents | Underwater salient object detection (USOD) has attracted increasing attention for underwater visual scene understanding and vision-guided robotic applications. However, existing USOD methods still struggle with underwater image degradations, which often lead to inaccurate object localization, fragmented salient regions, and coarse boundary prediction. To address these challenges, this paper proposes DSS-USOD, a novel RGB-based USOD method built upon dynamic structural specialization. DSS-USOD extracts a shared base representation from a single underwater image, decomposes it into boundary-sensitive and region-coherent structural features, and dynamically coordinates their contributions according to local structural context. Specifically, the extracted shared base representation is decomposed into a boundary-sensitive branch for modeling fine-grained boundary details and a region-coherent branch for capturing region-level structural consistency. A spatial coordination module is then introduced to adaptively regulate the relative contributions of the two branches according to local structural context. Moreover, cooperative structural supervision is introduced to promote branch specialization and stabilize spatial coordination, enabling DSS-USOD to better balance boundary precision and region coherence under degraded underwater conditions. Extensive experiments show that DSS-USOD achieves superior performance on benchmark datasets. Finally, real-world deployment on an underwater robot validates the practical effectiveness of DSS-USOD for underwater object inspection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15535 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Dynamic Structural Specialization for Underwater Salient Object Detection Hong, Lin Wang, Chenhui Deng, Linan Cui, Yuning Zhang, Yu Wang, Xin Zhang, Bojian Ren, Wenqi Yang, Xingchen Zhang, Fumin Computer Vision and Pattern Recognition Underwater salient object detection (USOD) has attracted increasing attention for underwater visual scene understanding and vision-guided robotic applications. However, existing USOD methods still struggle with underwater image degradations, which often lead to inaccurate object localization, fragmented salient regions, and coarse boundary prediction. To address these challenges, this paper proposes DSS-USOD, a novel RGB-based USOD method built upon dynamic structural specialization. DSS-USOD extracts a shared base representation from a single underwater image, decomposes it into boundary-sensitive and region-coherent structural features, and dynamically coordinates their contributions according to local structural context. Specifically, the extracted shared base representation is decomposed into a boundary-sensitive branch for modeling fine-grained boundary details and a region-coherent branch for capturing region-level structural consistency. A spatial coordination module is then introduced to adaptively regulate the relative contributions of the two branches according to local structural context. Moreover, cooperative structural supervision is introduced to promote branch specialization and stabilize spatial coordination, enabling DSS-USOD to better balance boundary precision and region coherence under degraded underwater conditions. Extensive experiments show that DSS-USOD achieves superior performance on benchmark datasets. Finally, real-world deployment on an underwater robot validates the practical effectiveness of DSS-USOD for underwater object inspection. |
| title | Learning Dynamic Structural Specialization for Underwater Salient Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.15535 |