Learning Dynamic Structural Specialization for Underwater Salient Object Detection

TL;DR

This paper introduces DSS-USOD, a novel RGB-based underwater salient object detection method that dynamically combines boundary-sensitive and region-coherent features to improve accuracy under challenging underwater conditions.

Contribution

The paper proposes a dynamic structural specialization framework with a spatial coordination module and cooperative supervision for improved underwater salient object detection.

Findings

DSS-USOD outperforms existing methods on benchmark datasets.

The method achieves better boundary precision and region coherence.

Real-world underwater robot deployment confirms practical effectiveness.

Abstract

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.