mlsanityData to 7 Oct 2026

HRFormer: High-Resolution Transformer for Dense Prediction

arXiv 2110.09408 ↗First posted 18 Oct 2021cs.CVcited by 149

Not on the map. Why?

Abstract (arXiv)

We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost. We take advantage of the multi-resolution parallel design introduced in high-resolution convolutional networks (HRNet), along with local-window self-attention that performs self-attention over small non-overlapping image windows, for improving the memory and computation efficiency. In addition, we introduce a convolution into the FFN to exchange information across the disconnected image windows. We demonstrate the effectiveness of the High-Resolution Transformer on both human pose estimation and semantic segmentation tasks, e.g., HRFormer outperforms Swin transformer by 1.3 AP on COCO pose estimation with 50% fewer parameters and 30% fewer FLOPs. Code is available at: https://github.com/HRNet/HRFormer.

Key facts. Cited by 149 papers in the map (data through 7 Oct 2026). Builds on 57 of its 63 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

57 of 63 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
38 more
  1. 2016Pyramid Scene Parsing Networkcited by 2,472
  2. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  3. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  7. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  12. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  13. 2020Designing Network Design Spacescited by 954
  14. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  15. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  16. 2021Multiscale Vision Transformerscited by 896
  17. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  18. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  19. 2021Going deeper with Image Transformerscited by 759
  20. 2021Transformer in Transformercited by 632
  21. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  22. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  23. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  24. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  25. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  26. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  27. 2021Early Convolutions Help Transformers See Bettercited by 395
  28. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  29. 2021Video Transformer Networkcited by 271
  30. 2021Incorporating Convolution Designs into Visual Transformerscited by 248
  31. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  32. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  33. 2019Local Relation Networks for Image Recognitioncited by 210
  34. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  35. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  36. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  37. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  38. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 49; 2023: 38; 2024: 29; 2025: 18; 2026: 9.

149 papers.

Sort:

By area:

  1. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  2. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  3. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  4. 2022Vision Transformer with Deformable Attentioncited by 293
  5. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 229
  6. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  7. 2022DaViT: Dual Attention Vision Transformerscited by 174
  8. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  9. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  10. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  11. 2021A Survey of Visual Transformerscited by 117
  12. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
38 more
  1. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 94
  2. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  3. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  4. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  5. 2022TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentationcited by 82
  6. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 71
  7. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  8. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  9. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  10. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  11. 2022APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Trackingcited by 55
  12. 2023Human Pose as Compositional Tokenscited by 45
  13. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  14. 2022MixFormer: Mixing Features across Windows and Dimensionscited by 43
  15. 2022PseudoClick: Interactive Image Segmentation with Click Imitationcited by 42
  16. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  17. 2025DICEPTION: A Generalist Diffusion Model for Visual Perceptual Taskscited by 37
  18. 2022ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformercited by 36
  19. 2022Tracking Objects as Pixel-wise Distributionscited by 36
  20. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  21. 2024Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localizationcited by 35
  22. 2022Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningcited by 33
  23. 2023HAP: Structure-Aware Masked Image Modeling for Human-Centric Perceptioncited by 33
  24. 2022HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detectioncited by 30
  25. 2025PolaFormer: Polarity-aware Linear Attention for Vision Transformerscited by 30
  26. 2021iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Imagescited by 27
  27. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  28. 2023Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Modelscited by 26
  29. 2022Self-Promoted Supervision for Few-Shot Transformercited by 22
  30. 2022Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolutioncited by 22
  31. 2023InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understandingcited by 22
  32. 2022Conditional DETR V2: Efficient Detection Transformer with Box Queriescited by 21
  33. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  34. 2022Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraintscited by 21
  35. 2022Bridged Transformer for Vision and Point Cloud 3D Object Detectioncited by 19
  36. 2023DFormer: Diffusion-guided Transformer for Universal Image Segmentationcited by 19
  37. 2021ELSA: Enhanced Local Self-Attention for Vision Transformercited by 18
  38. 2023SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognitioncited by 18

50 most cited of 149 All 149 (JSON)