# Lite-HRNet: A Lightweight High-Resolution Network

arXiv: https://arxiv.org/abs/2104.06403 · HTML: https://mlsanity.com/paper/2104.06403/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 62 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (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)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)

## Built on by (most cited first, 30 of 91)

- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling](https://mlsanity.com/paper/2204.13686/) (2022)
- [Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation](https://mlsanity.com/paper/2111.01236/) (2021)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [On the Connection between Local Attention and Dynamic Depth-wise Convolution](https://mlsanity.com/paper/2106.04263/) (2021)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection](https://mlsanity.com/paper/2301.03036/) (2023)
- [LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network](https://mlsanity.com/paper/2404.01614/) (2024)
- [MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2308.15300/) (2023)
- [A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose](https://mlsanity.com/paper/2111.12696/) (2021)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation](https://mlsanity.com/paper/2205.01271/) (2022)
- [Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation](https://mlsanity.com/paper/2109.03622/) (2021)
- [AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks](https://mlsanity.com/paper/2402.15351/) (2024)
- [HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs](https://mlsanity.com/paper/2403.11999/) (2024)
- [SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation](https://mlsanity.com/paper/2312.10758/) (2023)
- [Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs](https://mlsanity.com/paper/2404.10700/) (2024)
- [Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation](https://mlsanity.com/paper/2204.10762/) (2022)
- [HOD: A Benchmark Dataset for Harmful Object Detection](https://mlsanity.com/paper/2310.05192/) (2023)
- [FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER](https://mlsanity.com/paper/2205.15448/) (2022)
- [Widely Applicable Strong Baseline for Sports Ball Detection and Tracking](https://mlsanity.com/paper/2311.05237/) (2023)
- [MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment](https://mlsanity.com/paper/2407.21654/) (2024)
- [Lightweight Monocular Depth with a Novel Neural Architecture Search Method](https://mlsanity.com/paper/2108.11105/) (2021)
- [Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation](https://mlsanity.com/paper/2406.08896/) (2024)
- [On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild](https://mlsanity.com/paper/2307.10267/) (2023)
- [GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation](https://mlsanity.com/paper/2407.10756/) (2024)
- [Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer](https://mlsanity.com/paper/2408.15185/) (2024)

## 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.