mlsanityData to 7 Oct 2026

Greit-HRNet: Grouped Lightweight High-Resolution Network for Human Pose Estimation

arXiv 2407.07389 ↗First posted 10 Jul 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

As multi-scale features are necessary for human pose estimation tasks, high-resolution networks are widely applied. To improve efficiency, lightweight modules are proposed to replace costly point-wise convolutions in high-resolution networks, including channel weighting and spatial weighting methods. However, they fail to maintain the consistency of weights and capture global spatial information. To address these problems, we present a Grouped lightweight High-Resolution Network (Greit-HRNet), in which we propose a Greit block including a group method Grouped Channel Weighting (GCW) and a spatial weighting method Global Spatial Weighting (GSW). GCW modules group conditional channel weighting to make weights stable and maintain the high-resolution features with the deepening of the network, while GSW modules effectively extract global spatial information and exchange information across channels. In addition, we apply the Large Kernel Attention (LKA) method to improve the whole efficiency of our Greit-HRNet. Our experiments on both MS-COCO and MPII human pose estimation datasets demonstrate the superior performance of our Greit-HRNet, outperforming other state-of-the-art lightweight networks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 10 Jul 2024.

Builds on

24 of 33 references.

References · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  5. 2017Non-local Neural Networkscited by 2,290
  6. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  9. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  12. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
12 more
  1. 2022Visual Attention Networkcited by 210
  2. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
  3. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  4. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  5. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  6. 2023Efficient Multi-Scale Attention Module with Cross-Spatial Learningcited by 40
  7. 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
  8. 2020Multi-scale Grouped Dense Network for VVC Intra Codingcited by 10
  9. 2022Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimationcited by 10
  10. 2023Are Large Kernels Better Teachers than Transformers for ConvNets?cited by 8
  11. 2022Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognitioncited by 4
  12. 2023X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attentioncited by 1

Built on by

Not cited yet.