mlsanityData to 14 Oct 2026

DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation

arXiv 2210.06747 ↗First posted 13 Oct 2022eess.IV cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Combining RGB images and the corresponding depth maps in semantic segmentation proves the effectiveness in the past few years. Existing RGB-D modal fusion methods either lack the non-linear feature fusion ability or treat both modal images equally, regardless of the intrinsic distribution gap or information loss. Here we find that depth maps are suitable to provide intrinsic fine-grained patterns of objects due to their local depth continuity, while RGB images effectively provide a global view. Based on this, we propose a pixel differential convolution attention (DCA) module to consider geometric information and local-range correlations for depth data. Furthermore, we extend DCA to ensemble differential convolution attention (EDCA) which propagates long-range contextual dependencies and seamlessly incorporates spatial distribution for RGB data. DCA and EDCA dynamically adjust convolutional weights by pixel difference to enable self-adaptive in local and long range, respectively. A two-branch network built with DCA and EDCA, called Differential Convolutional Network (DCANet), is proposed to fuse local and global information of two-modal data. Consequently, the individual advantage of RGB and depth data are emphasized. Our DCANet is shown to set a new state-of-the-art performance for RGB-D semantic segmentation on two challenging benchmark datasets, i.e., NYUDv2 and SUN-RGBD.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 46 of its 83 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

46 of 83 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2017Squeeze-and-Excitation Networkscited by 4,789
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  11. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  12. 2016Pyramid Scene Parsing Networkcited by 2,479
34 more
  1. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  2. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  3. 2017Non-local Neural Networkscited by 2,293
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  6. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2013Network In Networkcited by 605
  9. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  10. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  11. 2017Residual Attention Network for Image Classificationcited by 386
  12. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  13. 2020Exploring Self-attention for Image Recognitioncited by 313
  14. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  15. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  16. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  17. 2022Visual Attention Networkcited by 210
  18. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  19. 2015ParseNet: Looking Wider to See Bettercited by 177
  20. 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 139
  21. 2022Multimodal Token Fusion for Vision Transformerscited by 136
  22. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 127
  23. 2020Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentationcited by 122
  24. 2019ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentationcited by 107
  25. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  26. 2021ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentationcited by 77
  27. 2018Depth-aware CNN for RGB-D Segmentationcited by 74
  28. 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
  29. 2018RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentationcited by 66
  30. 2021InverseForm: A Loss Function for Structured Boundary-Aware Segmentationcited by 65
  31. 2020Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentationcited by 48
  32. 2022SATS: Self-Attention Transfer for Continual Semantic Segmentationcited by 25
  33. 2020Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsingcited by 24
  34. 2019Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Imagescited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 4; 2026: 2.

9 papers.

  1. 2024SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Trackingcited by 44
  2. 2023RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networkscited by 10
  3. 2023ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformercited by 3
  4. 2025Efficient Dual-domain Image Dehazing with Haze Prior Perceptioncited by 2
  5. 2025DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentationcited by 2
  6. 2025HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Frameworkcited by 1
  7. 2026RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentationcited by 1
  8. 2025Project-and-Fuse: Improving RGB-D Semantic Segmentation via Graph Convolution Networkscited by 0
  9. 2026Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropoutcited by 0