mlsanityData to 13 Oct 2026

STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detection

arXiv 2603.21999 ↗First posted 23 Mar 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest, owing to the transformer's exceptional capacity to capture long-range pixel dependencies. Nevertheless, current RGB-D SOD methods face challenges, such as the quadratic complexity of the attention mechanism and the limited local detail extraction. To overcome these limitations, we propose a novel Superpixel Token Enhancing Network (STENet), which introduces superpixels into cross-modal interaction. STENet follows the two-stream encoder-decoder structure. Its cores are two tailored superpixel-driven cross-modal interaction modules, responsible for global and local feature enhancement. Specifically, we update the superpixel generation method by expanding the neighborhood range of each superpixel, allowing for flexible transformation between pixels and superpixels. With the updated superpixel generation method, we first propose the Superpixel Attention Global Enhancing Module to model the global pixel-to-superpixel relationship rather than the traditional global pixel-to-pixel relationship, which can capture region-level information and reduce computational complexity. We also propose the Superpixel Attention Local Refining Module, which leverages pixel similarity within superpixels to filter out a subset of pixels (i.e., local pixels) and then performs feature enhancement on these local pixels, thereby capturing concerned local details. Furthermore, we fuse the globally and locally enhanced features along with the cross-scale features to achieve comprehensive feature representation. Experiments on seven RGB-D SOD datasets reveal that our STENet achieves competitive performance compared to state-of-the-art methods. The code and results of our method are available at https://github.com/Mark9010/STENet.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 37 of its 76 references that are in the map. First posted on arXiv 23 Mar 2026.

Builds on

37 of 76 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  6. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  7. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  8. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 230
  9. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  10. 2021CAT: Cross Attention in Vision Transformercited by 92
  11. 2018Superpixel Sampling Networkscited by 79
  12. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
25 more
  1. 2020A Single Stream Network for Robust and Real-time RGB-D Salient Object Detectioncited by 67
  2. 2020Siamese Network for RGB-D Salient Object Detection and Beyondcited by 67
  3. 2021Lite Vision Transformer with Enhanced Self-Attentioncited by 64
  4. 2022SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detectioncited by 59
  5. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  6. 2021CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detectioncited by 47
  7. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  8. 2022Vision Transformer with Super Token Samplingcited by 44
  9. 2022CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detectioncited by 38
  10. 2021RGB-D Salient Object Detection via 3D Convolutional Neural Networkscited by 36
  11. 2020Bilateral Attention Network for RGB-D Salient Object Detectioncited by 35
  12. 2021Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detectioncited by 33
  13. 2023HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awarenesscited by 31
  14. 2019Adaptive Fusion for RGB-D Salient Object Detectioncited by 29
  15. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  16. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  17. 2024Learning Adaptive Fusion Bank for Multi-modal Salient Object Detectioncited by 19
  18. 2023Salient Object Detection in Optical Remote Sensing Images Driven by Transformercited by 17
  19. 2021Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservationcited by 14
  20. 2022Semantic Segmentation by Early Region Proxycited by 14
  21. 2024SPFormer: Enhancing Vision Transformer with Superpixel Representationcited by 13
  22. 2023Superpixel Transformers for Efficient Semantic Segmentationcited by 12
  23. 2023Salient Object Detection in RGB-D Videoscited by 8
  24. 2023Texture-Semantic Collaboration Network for ORSI Salient Object Detectioncited by 3
  25. 2023No-Service Rail Surface Defect Segmentation via Normalized Attention and Dual-scale Interactioncited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidancecited by 1
  2. 2026Weakly-Supervised RGB-D Salient Object Detection via SAM-driven Pseudo Annotation and State Space Interaction-based Diffusioncited by 0