mlsanityData to 7 Oct 2026

Learning Spatially Adaptive Structural Coordination for Underwater Salient Object Detection

arXiv 2605.15535 ↗First posted 15 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Underwater salient object detection (USOD) has attracted increasing attention for underwater scene understanding and vision-guided robotic applications. However, the spatially non-uniform degradation in underwater images causes spatially varying reliability of structural cues: boundary-sensitive responses can enhance object contours but are vulnerable to degradation-induced noise, whereas region-coherent responses improve semantic completeness but may blur object boundaries. Existing methods rarely explicitly consider the spatial variation in structural cue reliability under underwater image degradation. To address this problem, this work proposes SASC-USOD, a novel framework for learning spatially adaptive structural coordination in USOD. The proposed framework constructs two complementary structural representations with different characteristics. A boundary-sensitive representation is obtained by combining fixed Laplacian filtering with a learnable local-detail transformation to enhance discriminative boundary information, while a region-coherent representation is generated through dual-range anisotropic large-kernel contextual aggregation to capture long-range structural consistency. A spatial coordination module is then introduced to estimate the relative reliability of these structural representations and adaptively coordinate their contributions according to image content. Extensive experiments on the USOD10K and USOD benchmarks demonstrate that SASC-USOD consistently outperforms existing methods, reducing MAE by 4.07% and 23.53% compared with the strongest competing method, respectively. Moreover, its lightweight variant runs at 21 FPS on an NVIDIA Jetson TX2 NX, demonstrating its capability for onboard underwater robotic perception.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 95 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

46 of 95 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  5. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  6. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  7. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  8. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  9. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  10. 2014The Secrets of Salient Object Segmentationcited by 200
  11. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  12. 2021Visual Saliency Transformercited by 175
34 more
  1. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  2. 2021Salient Object Detection via Integrity Learningcited by 133
  3. 2020Label Decoupling Framework for Salient Object Detectioncited by 111
  4. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  5. 2020JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detectioncited by 79
  6. 2021Specificity-preserving RGB-D Saliency Detectioncited by 70
  7. 2020A Single Stream Network for Robust and Real-time RGB-D Salient Object Detectioncited by 67
  8. 2020EDN: Salient Object Detection via Extremely-Downsampled Networkcited by 64
  9. 2023VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learningcited by 58
  10. 2020Accurate RGB-D Salient Object Detection via Collaborative Learningcited by 52
  11. 2018Selectivity or Invariance: Boundary-aware Salient Object Detectioncited by 48
  12. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  13. 2020Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detectioncited by 38
  14. 2022CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detectioncited by 38
  15. 2019Progressive Feature Polishing Network for Salient Object Detectioncited by 34
  16. 2021Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detectioncited by 34
  17. 2023HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awarenesscited by 31
  18. 2023VST++: Efficient and Stronger Visual Saliency Transformercited by 28
  19. 2021MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detectioncited by 27
  20. 2022UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robotscited by 27
  21. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  22. 2020Is Depth Really Necessary for Salient Object Detection?cited by 23
  23. 2024A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detectioncited by 23
  24. 2020SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robotscited by 20
  25. 2021Generative Transformer for Accurate and Reliable Salient Object Detectioncited by 18
  26. 2021Few-Cost Salient Object Detection with Adversarial-Paced Learningcited by 17
  27. 2019Edge-guided Non-local Fully Convolutional Network for Salient Object Detectioncited by 16
  28. 2021BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detectioncited by 15
  29. 2021Progressive Self-Guided Loss for Salient Object Detectioncited by 14
  30. 2021Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Netcited by 9
  31. 2025Rapid Salient Object Detection with Difference Convolutional Neural Networkscited by 9
  32. 2025Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspectivecited by 6
  33. 2022Salient Object Detection via Dynamic Scale Routingcited by 5
  34. 2021Perception-and-Regulation Network for Salient Object Detectioncited by 2

Built on by

Not cited yet.