Lite-HRNet: A Lightweight High-Resolution Network

Published in

Computer Vision and Pattern Recognition(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

An efficient high-resolution network, Lite-HRNet, is presented, which demonstrates superior results on human pose estimation over popular lightweight networks and can be easily applied to semantic segmentation task in the same lightweight manner.

Abstract

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 (1 × 1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1 × 1) 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 (1 × 1) 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.

Authors

Bin Xiao

6 papers

Changqian Yu

2 papers

N. Sang

4 papers

References62 items

Representative Graph Neural Network

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

Rethinking Bottleneck Structure for Efficient Mobile Network Design

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

3D Human Pose Estimation via Explicit Compositional Depth Maps

Lite-HRNet: A Lightweight High-Resolution Network

Published in

Computer Vision and Pattern Recognition(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Bin Xiao

6 papers

Changqian Yu

2 papers

N. Sang

4 papers

References62 items

Representative Graph Neural Network

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

Rethinking Bottleneck Structure for Efficient Mobile Network Design

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

3D Human Pose Estimation via Explicit Compositional Depth Maps

Changxin Gao

4 papers

Jingdong Wang

7 papers

Context Prior for Scene Segmentation

SOLOv2: Dynamic and Fast Instance Segmentation

Conditional Convolutions for Instance Segmentation

FasterSeg: Searching for Faster Real-time Semantic Segmentation

Dynamic Convolution: Attention Over Convolution Kernels

Distribution-Aware Coordinate Representation for Human Pose Estimation

Graph-Guided Architecture Search for Real-Time Semantic Segmentation

HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

Deep High-Resolution Representation Learning for Visual Recognition

MixConv: Mixed Depthwise Convolutional Kernels

Customizable Architecture Search for Semantic Segmentation

Searching for MobileNetV3

CondConv: Conditionally Parameterized Convolutions for Efficient Inference

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images

Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search

Fast-SCNN: Fast Semantic Segmentation Network

Deformable ConvNets V2: More Deformable, Better Results

Multi-path segmentation network

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

CBAM: Convolutional Block Attention Module

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks

Learning a Discriminative Feature Network for Semantic Segmentation

Simple Baselines for Human Pose Estimation and Tracking

Interleaved Structured Sparse Convolutional Neural Networks

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation

SkipNet: Learning Dynamic Routing in Convolutional Networks

Integral Human Pose Regression

Cascaded Pyramid Network for Multi-person Pose Estimation

Interleaved Group Convolutions

Squeeze-and-Excitation Networks

Learning Feature Pyramids for Human Pose Estimation

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Deformable Convolutional Networks

Towards Accurate Multi-person Pose Estimation in the Wild

Feature Pyramid Networks for Object Detection

Pyramid Scene Parsing Network

RMPE: Regional Multi-person Pose Estimation

Xception: Deep Learning with Depthwise Separable Convolutions

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Dynamic Filter Networks

The Cityscapes Dataset for Semantic Urban Scene Understanding

Stacked Hourglass Networks for Human Pose Estimation

Deep Residual Learning for Image Recognition

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Spatial Transformer Networks

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

Microsoft COCO: Common Objects in Context

ImageNet classification with deep convolutional neural networks

Field of Study

Computer Science

Journal Information

Name

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Page

10708-10717

Venue Information

Name

Computer Vision and Pattern Recognition

Type

conference

URL

https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147

Alternate Names

CVPR
Comput Vis Pattern Recognit

TL;DR

Abstract

Authors

References62 items

Representative Graph Neural Network

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

Rethinking Bottleneck Structure for Efficient Mobile Network Design

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

3D Human Pose Estimation via Explicit Compositional Depth Maps

TL;DR

Abstract

Authors

References62 items

Representative Graph Neural Network

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

Rethinking Bottleneck Structure for Efficient Mobile Network Design

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

3D Human Pose Estimation via Explicit Compositional Depth Maps

Context Prior for Scene Segmentation

SOLOv2: Dynamic and Fast Instance Segmentation

Dynamic ReLU

Conditional Convolutions for Instance Segmentation

FasterSeg: Searching for Faster Real-time Semantic Segmentation

Dynamic Convolution: Attention Over Convolution Kernels

Distribution-Aware Coordinate Representation for Human Pose Estimation

Graph-Guided Architecture Search for Real-Time Semantic Segmentation

HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

Deep High-Resolution Representation Learning for Visual Recognition

MixConv: Mixed Depthwise Convolutional Kernels

Customizable Architecture Search for Semantic Segmentation

Searching for MobileNetV3

CondConv: Conditionally Parameterized Convolutions for Efficient Inference

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images

Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search

Fast-SCNN: Fast Semantic Segmentation Network

Deformable ConvNets V2: More Deformable, Better Results

Multi-path segmentation network

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

CBAM: Convolutional Block Attention Module

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks

Learning a Discriminative Feature Network for Semantic Segmentation

Simple Baselines for Human Pose Estimation and Tracking

Interleaved Structured Sparse Convolutional Neural Networks

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation

SkipNet: Learning Dynamic Routing in Convolutional Networks

Integral Human Pose Regression

Cascaded Pyramid Network for Multi-person Pose Estimation

Interleaved Group Convolutions

Squeeze-and-Excitation Networks

Learning Feature Pyramids for Human Pose Estimation

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Mask R-CNN

Deformable Convolutional Networks

Meta Networks

Towards Accurate Multi-person Pose Estimation in the Wild

Feature Pyramid Networks for Object Detection

Pyramid Scene Parsing Network

RMPE: Regional Multi-person Pose Estimation

Xception: Deep Learning with Depthwise Separable Convolutions

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Dynamic Filter Networks

The Cityscapes Dataset for Semantic Urban Scene Understanding

Stacked Hourglass Networks for Human Pose Estimation

Deep Residual Learning for Image Recognition

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Spatial Transformer Networks

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

Microsoft COCO: Common Objects in Context

ImageNet classification with deep convolutional neural networks

Field of Study

Journal Information

Name

Page

Venue Information