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

arXiv: https://arxiv.org/abs/2407.07389 · HTML: https://mlsanity.com/paper/2407.07389/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Lite-HRNet: A Lightweight High-Resolution Network](https://mlsanity.com/paper/2104.06403/) (2021)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation](https://mlsanity.com/paper/2205.01271/) (2022)
- [Multi-scale Grouped Dense Network for VVC Intra Coding](https://mlsanity.com/paper/2005.07896/) (2020)
- [Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation](https://mlsanity.com/paper/2204.10762/) (2022)
- [Are Large Kernels Better Teachers than Transformers for ConvNets?](https://mlsanity.com/paper/2305.19412/) (2023)
- [Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognition](https://mlsanity.com/paper/2202.06673/) (2022)
- [X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention](https://mlsanity.com/paper/2310.08042/) (2023)

## 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.