Shortcuts

HRNet

Abstract

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems.

How to use it?

from mmpretrain import inference_model

predict = inference_model('hrnet-w18_3rdparty_8xb32_in1k', 'demo/bird.JPEG')
print(predict['pred_class'])
print(predict['pred_score'])

Models and results

Image Classification on ImageNet-1k

Model

Pretrain

Params (M)

Flops (G)

Top-1 (%)

Top-5 (%)

Config

Download

hrnet-w18_3rdparty_8xb32_in1k*

From scratch

21.30

4.33

76.75

93.44

config

model

hrnet-w30_3rdparty_8xb32_in1k*

From scratch

37.71

8.17

78.19

94.22

config

model

hrnet-w32_3rdparty_8xb32_in1k*

From scratch

41.23

8.99

78.44

94.19

config

model

hrnet-w40_3rdparty_8xb32_in1k*

From scratch

57.55

12.77

78.94

94.47

config

model

hrnet-w44_3rdparty_8xb32_in1k*

From scratch

67.06

14.96

78.88

94.37

config

model

hrnet-w48_3rdparty_8xb32_in1k*

From scratch

77.47

17.36

79.32

94.52

config

model

hrnet-w64_3rdparty_8xb32_in1k*

From scratch

128.06

29.00

79.46

94.65

config

model

hrnet-w18_3rdparty_8xb32-ssld_in1k*

From scratch

21.30

4.33

81.06

95.70

config

model

hrnet-w48_3rdparty_8xb32-ssld_in1k*

From scratch

77.47

17.36

83.63

96.79

config

model

Models with * are converted from the official repo. The config files of these models are only for inference. We haven’t reproduce the training results.

Citation

@article{WangSCJDZLMTWLX19,
  title={Deep High-Resolution Representation Learning for Visual Recognition},
  author={Jingdong Wang and Ke Sun and Tianheng Cheng and
          Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and
          Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao},
  journal={TPAMI},
  year={2019}
}
Read the Docs v: latest
Versions
latest
stable
mmcls-1.x
mmcls-0.x
dev
Downloads
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.