mlsanityData to 7 Oct 2026

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

arXiv 2301.03036 ↗First posted 8 Jan 2023cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output's fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level. The proposed model, named HRTransNet, first introduces an auxiliary stream for feature extraction of supplementary modality. Then, features are injected into the primary modality at the beginning of each multi-resolution branch. Next, HRFormer is applied to achieve forwarding propagation. Finally, all the output features with different resolutions are aggregated by intra-feature and inter-feature interactive transformers. Application of the proposed model results in impressive improvement for driving two-modality SOD tasks, e.g., RGB-D, RGB-T, and light field SOD.https://github.com/liuzywen/HRTransNet

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 68 of its 135 references that are in the map. First posted on arXiv 8 Jan 2023.

Builds on

68 of 135 references.

References · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  6. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  7. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  10. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  11. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  12. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
38 more
  1. 2018Efficient Attention: Attention with Linear Complexitiescited by 366
  2. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  3. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  4. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  5. 2021Visual Saliency Transformercited by 175
  6. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  7. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  8. 2015Salient Object Detection: A Benchmarkcited by 130
  9. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  10. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  11. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  12. 2020Learning Dynamic Routing for Semantic Segmentationcited by 79
  13. 2020RGB-D Salient Object Detection: A Surveycited by 73
  14. 2021Specificity-preserving RGB-D Saliency Detectioncited by 70
  15. 2020RGBT Salient Object Detection: A Large-scale Dataset and Benchmarkcited by 69
  16. 2020Siamese Network for RGB-D Salient Object Detection and Beyondcited by 67
  17. 2018Review of Visual Saliency Detection with Comprehensive Informationcited by 60
  18. 2022SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detectioncited by 59
  19. 2019RGB-T Image Saliency Detection via Collaborative Graph Learningcited by 58
  20. 2021Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Predictioncited by 57
  21. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  22. 2017A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approachcited by 51
  23. 2021CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detectioncited by 47
  24. 2020DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detectioncited by 45
  25. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  26. 2020Multi-interactive Dual-decoder for RGB-thermal Salient Object Detectioncited by 44
  27. 2021HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformerscited by 39
  28. 2021RGB-D Salient Object Detection via 3D Convolutional Neural Networkscited by 36
  29. 2019Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregationcited by 34
  30. 2021Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detectioncited by 34
  31. 2021RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Imagescited by 34
  32. 2017Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusioncited by 28
  33. 2018Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Mapscited by 26
  34. 2021Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detectioncited by 24
  35. 2022Global-and-Local Collaborative Learning for Co-Salient Object Detectioncited by 24
  36. 2021Densely Nested Top-Down Flows for Salient Object Detectioncited by 23
  37. 2021Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognitioncited by 23
  38. 2019cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networkscited by 21

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 12; 2025: 3; 2026: 6.

27 papers.

Sort:

By area:

  1. 2023VST++: Efficient and Stronger Visual Saliency Transformercited by 28
  2. 2024Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmarkcited by 19
  3. 2024Learning Adaptive Fusion Bank for Multi-modal Salient Object Detectioncited by 19
  4. 2023Object Segmentation by Mining Cross-Modal Semanticscited by 12
  5. 2023Unified-modal Salient Object Detection via Adaptive Prompt Learningcited by 9
  6. 2023Salient Object Detection in RGB-D Videoscited by 8
  7. 2024Quality-aware Selective Fusion Network for V-D-T Salient Object Detectioncited by 8
  8. 2024SSFam: Scribble Supervised Salient Object Detection Familycited by 6
  9. 2024Part-Whole Relational Fusion Towards Multi-Modal Scene Understandingcited by 6
  10. 2023M3Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detectioncited by 4
  11. 2023ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformercited by 3
  12. 2025SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detectioncited by 3
15 more
  1. 2024Deep Fourier-embedded Network for RGB and Thermal Salient Object Detectioncited by 2
  2. 2026STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detectioncited by 2
  3. 2026RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradationcited by 2
  4. 2024A Volumetric Saliency Guided Image Summarization for RGB-D Indoor Scene Classificationcited by 1
  5. 2024Leveraging High-Resolution Features for Improved Deep Hashing-based Image Retrievalcited by 1
  6. 2024Intra-task Mutual Attention based Vision Transformer for Few-Shot Learningcited by 1
  7. 2024Class-relevant Patch Embedding Selection for Few-Shot Image Classificationcited by 1
  8. 2024Efficient Fourier Filtering Network with Contrastive Learning for AAV-based Unaligned Bimodal Salient Object Detectioncited by 1
  9. 2024FIPGNet:Pyramid grafting network with feature interaction strategiescited by 0
  10. 2025SSNet: Saliency Prior and State Space Model-based Network for Salient Object Detection in RGB-D Imagescited by 0
  11. 2025Unleashing the Power of Motion and Depth: A Selective Fusion Strategy for RGB-D Video Salient Object Detectioncited by 0
  12. 2026RSONet: Region-guided Selective Optimization Network for RGB-T Salient Object Detectioncited by 0
  13. 2026Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detectioncited by 0
  14. 2026M4-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detectioncited by 0
  15. 2026S2A:Semantic-to-Spatial Alignment for Alignment-Free RGB-T Salient Object Detectioncited by 0