Litcius/Paper detail

Turbidity–Similarity Decoupling: Feature-Consistent Mutual Learning for Underwater Salient Object Detection

Wujie Zhou, Beibei Tang, Runmin Cong, Qiuping Jiang

2026IEEE Transactions on Image Processing7 citationsDOI

Abstract

Underwater salient object detection (USOD) faces two major challenges that hinder accurate detection: substantial image noise owing to water turbidity and low foreground-background contrast caused by high visual similarity. In this study, a dual-model architecture based on mutual learning is proposed to address these issues. First, DenoisedNet, which focuses on addressing water turbidity issues, is developed. Using a separation-denoising-enhancement processing framework, it suppresses noise while maintaining target feature integrity through domain separation and cleaning enhancement modules. Second, SearchNet is designed to address the foreground-background similarity issue. It achieves precise localization through pseudo-label generation and layer-by-layer search mechanisms. To enable both networks to address these challenges collaboratively, a feature-consistent mutual-learning strategy is proposed, which aligns encoded features and prediction results, via evaluation and cross modes, respectively. This strategy enables their respective strengths to be complemented and the challenges of USOD to be solved more comprehensively. Our DenoisedNet and SearchNet outperform the best existing methods on the USOD10K and USOD benchmarks, achieving MAE improvements of 4.52%/5.52% and 1.61%/8.94%, respectively. The source code is available at https://github.com/BeibeiIsFreshman/DSNet_CL.

Topics & Concepts

Computer scienceArtificial intelligenceObject detectionSalientComputer visionNoise (video)Pattern recognition (psychology)Code (set theory)UnderwaterFeature extractionFeature (linguistics)Similarity (geometry)Mutual informationDomain (mathematical analysis)Orientation (vector space)Noise reductionObject (grammar)Image (mathematics)Image processingFeature learningVisualizationContrast (vision)Deep learningImage segmentationCognitive neuroscience of visual object recognitionVisibilityNoise measurementSource codeObject-class detectionMetric (unit)Artificial neural networkMachine learningImage Enhancement TechniquesAdvanced Neural Network ApplicationsWater Quality Monitoring Technologies
Turbidity–Similarity Decoupling: Feature-Consistent Mutual Learning for Underwater Salient Object Detection | Litcius