mlsanityData to 7 Oct 2026

U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction

arXiv 2210.07140 ↗First posted 13 Oct 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

High resolution and advanced semantic representation are both vital for dense prediction. Empirically, low-resolution feature maps often achieve stronger semantic representation, and high-resolution feature maps generally can better identify local features such as edges, but contains weaker semantic information. Existing state-of-the-art frameworks such as HRNet has kept low-resolution and high-resolution feature maps in parallel, and repeatedly exchange the information across different resolutions. However, we believe that the lowest-resolution feature map often contains the strongest semantic information, and it is necessary to go through more layers to merge with high-resolution feature maps, while for high-resolution feature maps, the computational cost of each convolutional layer is very large, and there is no need to go through so many layers. Therefore, we designed a U-shaped High-Resolution Network (U-HRNet), which adds more stages after the feature map with strongest semantic representation and relaxes the constraint in HRNet that all resolutions need to be calculated parallel for a newly added stage. More calculations are allocated to low-resolution feature maps, which significantly improves the overall semantic representation. U-HRNet is a substitute for the HRNet backbone and can achieve significant improvement on multiple semantic segmentation and depth prediction datasets, under the exactly same training and inference setting, with almost no increasing in the amount of calculation. Code is available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 71 of its 87 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

71 of 87 references.

References · 71

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  11. 2016Pyramid Scene Parsing Networkcited by 2,472
  12. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
38 more
  1. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  2. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  3. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  6. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  7. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  8. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  9. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  10. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  11. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  12. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  13. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  14. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  15. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  16. 2018Context Encoding for Semantic Segmentationcited by 289
  17. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 271
  18. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
  19. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  20. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  21. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  22. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  23. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  24. 2016Wider or Deeper: Revisiting the ResNet Model for Visual Recognitioncited by 184
  25. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  26. 2017Understanding Convolution for Semantic Segmentationcited by 168
  27. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  28. 2018Pyramid Attention Network for Semantic Segmentationcited by 148
  29. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  30. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  31. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  32. 2020Semantic Flow for Fast and Accurate Scene Parsingcited by 128
  33. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  34. 2017Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsingcited by 109
  35. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  36. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  37. 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
  38. 2016Full-Resolution Residual Networks for Semantic Segmentation in Street Scenescited by 71

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 1; 2026: 1.

3 papers.

  1. 2023Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentationcited by 10
  2. 2025Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessmentcited by 5
  3. 2026MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learningcited by 1