DeepAI AI Chat
Log In Sign Up

High-Resolution Representations for Labeling Pixels and Regions

04/09/2019
by   Ke Sun, et al.
Huazhong University of Science u0026 Technology
Microsoft
Peking University
Griffith University
USTC
6

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet) SunXLW19, recently developed for human pose estimation, maintains high-resolution representations through the whole process by connecting high-to-low resolution convolutions in parallel and produces strong high-resolution representations by repeatedly conducting fusions across parallel convolutions. In this paper, we conduct a further study on high-resolution representations by introducing a simple yet effective modification and apply it to a wide range of vision tasks. We augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from the high-resolution convolution as done in SunXLW19. This simple modification leads to stronger representations, evidenced by superior results. We show top results in semantic segmentation on Cityscapes, LIP, and PASCAL Context, and facial landmark detection on AFLW, COFW, 300W, and WFLW. In addition, we build a multi-level representation from the high-resolution representation and apply it to the Faster R-CNN object detection framework and the extended frameworks. The proposed approach achieves superior results to existing single-model networks on COCO object detection. The code and models have been publicly available at <https://github.com/HRNet>.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/20/2019

Deep High-Resolution Representation Learning for Visual Recognition

High-resolution representations are essential for position-sensitive vis...
04/13/2021

Lite-HRNet: A Lightweight High-Resolution Network

We present an efficient high-resolution network, Lite-HRNet, for human p...
04/22/2022

Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation

A high-resolution network exhibits remarkable capability in extracting m...
11/15/2016

OctNet: Learning Deep 3D Representations at High Resolutions

We present OctNet, a representation for deep learning with sparse 3D dat...
10/17/2022

Deformably-Scaled Transposed Convolution

Transposed convolution is crucial for generating high-resolution outputs...
03/30/2023

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

High-resolution images enable neural networks to learn richer visual rep...

Code Repositories

semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset


view repo

HRNet-Image-Classification

Train the HRNet model on ImageNet


view repo

tf-hrnet

tensorflow implementation for "High-Resolution Representations for Labeling Pixels and Regions"


view repo

Mish-semantic-segmentation-pytorch

None


view repo

semantic-segmentation

Simple inference implementation with trained HRNet.


view repo