mlsanityData to 7 Oct 2026

Lite-HRNet: A Lightweight High-Resolution Network

arXiv 2104.06403 ↗First posted 13 Apr 2021cs.CVcited by 91

Not on the map. Why?

Abstract (arXiv)

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet. We find that the heavily-used pointwise (1x1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1x1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner. The code and models have been publicly available at https://github.com/HRNet/Lite-HRNet.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 56 of its 62 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

56 of 62 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  10. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  11. 2019Searching for MobileNetV3cited by 1,984
  12. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
38 more
  1. 2017Deformable Convolutional Networkscited by 1,481
  2. 2015Spatial Transformer Networkscited by 1,423
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  8. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  9. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  12. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  13. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  14. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  15. 2016Dynamic Filter Networkscited by 318
  16. 2020Conditional Convolutions for Instance Segmentationcited by 314
  17. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  18. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  19. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  20. 2017Meta Networkscited by 268
  21. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  22. 2017Integral Human Pose Regressioncited by 255
  23. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  24. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  25. 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 138
  26. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  27. 2019Fast-SCNN: Fast Semantic Segmentation Networkcited by 124
  28. 2020Context Prior for Scene Segmentationcited by 121
  29. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  30. 2019MixConv: Mixed Depthwise Convolutional Kernelscited by 108
  31. 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
  32. 2019In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Imagescited by 99
  33. 2019FasterSeg: Searching for Faster Real-time Semantic Segmentationcited by 73
  34. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  35. 2020Dynamic ReLUcited by 55
  36. 2020Rethinking Bottleneck Structure for Efficient Mobile Network Designcited by 54
  37. 2019Customizable Architecture Search for Semantic Segmentationcited by 41
  38. 2019Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Searchcited by 39

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 17; 2023: 20; 2024: 23; 2025: 13; 2026: 8.

91 papers.

Sort:

By area:

  1. 2021Conditional DETR for Fast Training Convergencecited by 422
  2. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  3. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  4. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  5. 2022Changer: Feature Interaction is What You Need for Change Detectioncited by 78
  6. 2021On the Connection between Local Attention and Dynamic Depth-wise Convolutioncited by 61
  7. 2022DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimationcited by 29
  8. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  9. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  10. 2024LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Networkcited by 27
  11. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  12. 2021A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Posecited by 21
38 more
  1. 20222D Human Pose Estimation: A Surveycited by 21
  2. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  3. 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
  4. 2021Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimationcited by 14
  5. 2024AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Taskscited by 14
  6. 2024HIRI-ViT: Scaling Vision Transformer with High Resolution Inputscited by 12
  7. 2023SHaRPose: Sparse High-Resolution Representation for Human Pose Estimationcited by 11
  8. 2024Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPscited by 11
  9. 2022Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimationcited by 10
  10. 2023HOD: A Benchmark Dataset for Harmful Object Detectioncited by 10
  11. 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
  12. 2023Widely Applicable Strong Baseline for Sports Ball Detection and Trackingcited by 9
  13. 2024MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignmentcited by 9
  14. 2024Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulationcited by 7
  15. 2021Lightweight Monocular Depth with a Novel Neural Architecture Search Methodcited by 6
  16. 2023On the Real-Time Semantic Segmentation of Aphid Clusters in the Wildcited by 6
  17. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  18. 2024Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformercited by 6
  19. 2025TD-RD: A Top-Down Benchmark with Real-Time Framework for Road Damage Detectioncited by 6
  20. 20223D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspectivecited by 5
  21. 2022Lightweight and Progressively-Scalable Networks for Semantic Segmentationcited by 4
  22. 2023dugMatting: Decomposed-Uncertainty-Guided Mattingcited by 4
  23. 2023Efficient Vision Transformer for Human Pose Estimation via Patch Selectioncited by 4
  24. 2023Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentationcited by 4
  25. 2023Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Inputcited by 4
  26. 2024PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptionscited by 4
  27. 2024DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphonescited by 4
  28. 2025High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimationcited by 4
  29. 20222D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraintscited by 3
  30. 2024Domain Generalization for In-Orbit 6D Pose Estimationcited by 3
  31. 2024Benchmarking 2D Egocentric Hand Pose Datasetscited by 3
  32. 2021CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentationcited by 2
  33. 2022Simple and Efficient Architectures for Semantic Segmentationcited by 2
  34. 2022A View Independent Classification Framework for Yoga Posturescited by 2
  35. 2022Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphscited by 2
  36. 2022Efficient Heterogeneous Video Segmentation at the Edgecited by 2
  37. 2023Tomato Maturity Recognition with Convolutional Transformerscited by 2
  38. 2023Lite-HRNet Plus: Fast and Accurate Facial Landmark Detectioncited by 2

50 most cited of 91 All 91 (JSON)