HRNet, or High-Resolution Net, is a general purpose convolutional neural network for tasks like semantic segmentation, object detection and image classification. It is able to maintain high resolution representations through the whole process. We start from a high-resolution convolution stream, gradually add high-to-low resolution convolution streams one by one, and connect the multi-resolution streams in parallel. The resulting network consists of several ($4$ in the paper) stages and the $n$th stage contains $n$ streams corresponding to $n$ resolutions. We conduct repeated multi-resolution fusions by exchanging the information across the parallel streams over and over.

Source: Deep High-Resolution Representation Learning for Visual Recognition

Latest Papers

PAPER DATE
Monocular Expressive Body Regression through Body-Driven Attention
| Vasileios ChoutasGeorgios PavlakosTimo BolkartDimitrios TzionasMichael J. Black
2020-08-20
How to Train Your Robust Human Pose Estimator: Pay Attention to the Constraint Cue
Junjie HuangZheng ZhuGuan HuangDalong Du
2020-08-17
Structured Convolutions for Efficient Neural Network Design
Yash BhalgatYizhe ZhangJamie LinFatih Porikli
2020-08-06
EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
Christopher NeffAneri ShethSteven FurgursonHamed Tabkhi
2020-07-16
Unstructured Road Vanishing Point Detection Using the Convolutional Neural Network and Heatmap Regression
Yin-Bo LiuMing ZengQing-Hao Meng
2020-06-08
GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling
| Zhuoying WangYongtao WangZhi TangYangyan LiYing ChenHaibin LingWeisi Lin
2020-05-27
CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents
| Devashish PrasadAyan GadpalKshitij KapadniManish VisaveKavita Sultanpure
2020-04-27
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
| Bowen ChengBin XiaoJingdong WangHouhui ShiThomos S. HuangLei Zhang
2020-03-12
DNANet: De-Normalized Attention Based Multi-Resolution Network for Human Pose Estimation
Kun ZhangPeng HePing YaoGe ChenChuanguang YangHuimin LiLi FuTianyao Zheng
2019-09-11
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
| Bowen ChengBin XiaoJingdong WangHonghui ShiThomas S. HuangLei Zhang
2019-08-27
Deep High-Resolution Representation Learning for Visual Recognition
| Jingdong WangKe SunTianheng ChengBorui JiangChaorui DengYang ZhaoDong LiuYadong MuMingkui TanXinggang WangWenyu LiuBin Xiao
2019-08-20
Deep High-Resolution Representation Learning for Visual Recognition
| Jingdong WangKe SunTianheng ChengBorui JiangChaorui DengYang ZhaoDong LiuYadong MuMingkui TanXinggang WangWenyu LiuBin Xiao
2019-08-20

Categories