mlsanityData to 7 Oct 2026

Dual Mutual Learning Network with Global-local Awareness for RGB-D Salient Object Detection

arXiv 2501.01648 ↗First posted 3 Jan 2025cs.CV cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

RGB-D salient object detection (SOD), aiming to highlight prominent regions of a given scene by jointly modeling RGB and depth information, is one of the challenging pixel-level prediction tasks. Recently, the dual-attention mechanism has been devoted to this area due to its ability to strengthen the detection process. However, most existing methods directly fuse attentional cross-modality features under a manual-mandatory fusion paradigm without considering the inherent discrepancy between the RGB and depth, which may lead to a reduction in performance. Moreover, the long-range dependencies derived from global and local information make it difficult to leverage a unified efficient fusion strategy. Hence, in this paper, we propose the GL-DMNet, a novel dual mutual learning network with global-local awareness. Specifically, we present a position mutual fusion module and a channel mutual fusion module to exploit the interdependencies among different modalities in spatial and channel dimensions. Besides, we adopt an efficient decoder based on cascade transformer-infused reconstruction to integrate multi-level fusion features jointly. Extensive experiments on six benchmark datasets demonstrate that our proposed GL-DMNet performs better than 24 RGB-D SOD methods, achieving an average improvement of ~3% across four evaluation metrics compared to the second-best model (S3Net). Codes and results are available at https://github.com/kingkung2016/GL-DMNet.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 77 references that are in the map. First posted on arXiv 3 Jan 2025.

Builds on

37 of 77 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  8. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  9. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  10. 2019Selective Kernel Networkscited by 401
  11. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  12. 2021Visual Saliency Transformercited by 175
25 more
  1. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  2. 2015Salient Object Detection: A Benchmarkcited by 130
  3. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  4. 2020Strip Pooling: Rethinking Spatial Pooling for Scene Parsingcited by 114
  5. 2020RGB-D Salient Object Detection: A Surveycited by 73
  6. 2020Siamese Network for RGB-D Salient Object Detection and Beyondcited by 67
  7. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  8. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  9. 2020Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detectioncited by 38
  10. 2022CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detectioncited by 38
  11. 2020Bilateral Attention Network for RGB-D Salient Object Detectioncited by 35
  12. 2021Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detectioncited by 34
  13. 2021Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detectioncited by 33
  14. 2023HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awarenesscited by 31
  15. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  16. 2022Cross-Modality Deep Feature Learning for Brain Tumor Segmentationcited by 22
  17. 2019cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networkscited by 21
  18. 2020Depth Quality Aware Salient Object Detectioncited by 17
  19. 2020Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detectioncited by 13
  20. 2023Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detectioncited by 9
  21. 2022GroupTransNet: Group Transformer Network for RGB-D Salient Object Detectioncited by 7
  22. 2024Mixture of Experts with Mixture of Precisions for Tuning Quality of Servicecited by 7
  23. 2022Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detectioncited by 3
  24. 2021M2RNet: Multi-modal and Multi-scale Refined Network for RGB-D Salient Object Detectioncited by 2
  25. 2022Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Imagescited by 2

Built on by

Not cited yet.