mlsanityData to 14 Oct 2026

SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection

arXiv 2207.07898 ↗First posted 16 Jul 2022cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

RGB-D salient object detection (SOD) has been in the spotlight recently because it is an important preprocessing operation for various vision tasks. However, despite advances in deep learning-based methods, RGB-D SOD is still challenging due to the large domain gap between an RGB image and the depth map and low-quality depth maps. To solve this problem, we propose a novel superpixel prototype sampling network (SPSN) architecture. The proposed model splits the input RGB image and depth map into component superpixels to generate component prototypes. We design a prototype sampling network so that the network only samples prototypes corresponding to salient objects. In addition, we propose a reliance selection module to recognize the quality of each RGB and depth feature map and adaptively weight them in proportion to their reliability. The proposed method makes the model robust to inconsistencies between RGB images and depth maps and eliminates the influence of non-salient objects. Our method is evaluated on five popular datasets, achieving state-of-the-art performance. We prove the effectiveness of the proposed method through comparative experiments.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 29 of its 54 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

29 of 54 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2017Non-local Neural Networkscited by 2,293
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  10. 2018Self-Attention Generative Adversarial Networkscited by 809
  11. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  12. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
17 more
  1. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  2. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  3. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  4. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  5. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  6. 2015Salient Object Detection: A Benchmarkcited by 131
  7. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  8. 2020JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detectioncited by 79
  9. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  10. 2020Accurate RGB-D Salient Object Detection via Collaborative Learningcited by 52
  11. 2018Salient Objects in Clutter: Bringing Salient Object Detection to the Foregroundcited by 47
  12. 2020Cross-Modal Weighting Network for RGB-D Salient Object Detectioncited by 47
  13. 2016RGBD Salient Object Detection via Deep Fusioncited by 46
  14. 2020Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detectioncited by 40
  15. 2020Cascade Graph Neural Networks for RGB-D Salient Object Detectioncited by 36
  16. 2017Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusioncited by 28
  17. 2021Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Losscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 7; 2025: 6; 2026: 4.

26 papers.

Sort:

By area:

  1. 2023DFormer: Rethinking RGBD Representation Learning for Semantic Segmentationcited by 60
  2. 2023VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learningcited by 58
  3. 2022Source-free Depth for Object Pop-outcited by 52
  4. 2023HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awarenesscited by 31
  5. 2024Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalitiescited by 31
  6. 2023VST++: Efficient and Stronger Visual Saliency Transformercited by 28
  7. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  8. 2024Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentationcited by 22
  9. 2025Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Wellcited by 14
  10. 2025Improving SAM for Camouflaged Object Detection via Dual Stream Adapterscited by 13
  11. 2023Object Segmentation by Mining Cross-Modal Semanticscited by 12
  12. 2024MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selectioncited by 12
14 more
  1. 2025Reversible Unfolding Network for Concealed Visual Perception with Generative Refinementcited by 11
  2. 2025Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularizationcited by 9
  3. 2024ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detectioncited by 6
  4. 2023Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depthcited by 4
  5. 2025Differentiable Hierarchical Visual Tokenizationcited by 4
  6. 2024CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detectioncited by 3
  7. 2025Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentationcited by 3
  8. 2024Depth-guided Texture Diffusion for Image Semantic Segmentationcited by 2
  9. 2024Efficient Fourier Filtering Network with Contrastive Learning for AAV-based Unaligned Bimodal Salient Object Detectioncited by 1
  10. 2023Adaptive Graph Convolution Module for Salient Object Detectioncited by 0
  11. 2026Conditional Polarization Guidance for Camouflaged Object Detectioncited by 0
  12. 2026Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detectioncited by 0
  13. 2026DGSSM: Diffusion guided state-space models for multimodal salient object detectioncited by 0
  14. 2026Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detectioncited by 0