Method Details

Details for method 'HRNetV2'

name	HRNetV2
challenge	pixel-level semantic labeling
details	The high-resolution network (HRNet) 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.
publication	High-Resolution Representations for Labeling Pixels and Regions Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, Jingdong Wang https://arxiv.org/abs/1904.04514
project page / code	https://github.com/HRNet
used Cityscapes data	fine annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	February, 2019
previous submissions