Deep High-Resolution Representation Learning for Human Pose Estimation
Introduction
[ALGORITHM]
@inproceedings{SunXLW19,
title={Deep High-Resolution Representation Learning for Human Pose Estimation},
author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
booktitle={CVPR},
year={2019}
}
Results and models
Cityscapes
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| FCN |
HRNetV2p-W18-Small |
512x1024 |
40000 |
1.7 |
23.74 |
73.86 |
75.91 |
model | log |
| FCN |
HRNetV2p-W18 |
512x1024 |
40000 |
2.9 |
12.97 |
77.19 |
78.92 |
model | log |
| FCN |
HRNetV2p-W48 |
512x1024 |
40000 |
6.2 |
6.42 |
78.48 |
79.69 |
model | log |
| FCN |
HRNetV2p-W18-Small |
512x1024 |
80000 |
- |
- |
75.31 |
77.48 |
model | log |
| FCN |
HRNetV2p-W18 |
512x1024 |
80000 |
- |
- |
78.65 |
80.35 |
model | log |
| FCN |
HRNetV2p-W48 |
512x1024 |
80000 |
- |
- |
79.93 |
80.72 |
model | log |
| FCN |
HRNetV2p-W18-Small |
512x1024 |
160000 |
- |
- |
76.31 |
78.31 |
model | log |
| FCN |
HRNetV2p-W18 |
512x1024 |
160000 |
- |
- |
78.80 |
80.74 |
model | log |
| FCN |
HRNetV2p-W48 |
512x1024 |
160000 |
- |
- |
80.65 |
81.92 |
model | log |
ADE20K
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| FCN |
HRNetV2p-W18-Small |
512x512 |
80000 |
3.8 |
38.66 |
31.38 |
32.45 |
model | log |
| FCN |
HRNetV2p-W18 |
512x512 |
80000 |
4.9 |
22.57 |
35.51 |
36.80 |
model | log |
| FCN |
HRNetV2p-W48 |
512x512 |
80000 |
8.2 |
21.23 |
41.90 |
43.27 |
model | log |
| FCN |
HRNetV2p-W18-Small |
512x512 |
160000 |
- |
- |
33.00 |
34.55 |
model | log |
| FCN |
HRNetV2p-W18 |
512x512 |
160000 |
- |
- |
36.79 |
38.58 |
model | log |
| FCN |
HRNetV2p-W48 |
512x512 |
160000 |
- |
- |
42.02 |
43.86 |
model | log |
Pascal VOC 2012 + Aug
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| FCN |
HRNetV2p-W18-Small |
512x512 |
20000 |
1.8 |
43.36 |
65.20 |
68.55 |
model | log |
| FCN |
HRNetV2p-W18 |
512x512 |
20000 |
2.9 |
23.48 |
72.30 |
74.71 |
model | log |
| FCN |
HRNetV2p-W48 |
512x512 |
20000 |
6.2 |
22.05 |
75.87 |
78.58 |
model | log |
| FCN |
HRNetV2p-W18-Small |
512x512 |
40000 |
- |
- |
66.61 |
70.00 |
model | log |
| FCN |
HRNetV2p-W18 |
512x512 |
40000 |
- |
- |
72.90 |
75.59 |
model | log |
| FCN |
HRNetV2p-W48 |
512x512 |
40000 |
- |
- |
76.24 |
78.49 |
model | log |
Pascal Context
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| FCN |
HRNetV2p-W48 |
480x480 |
40000 |
6.1 |
8.86 |
45.14 |
47.42 |
model | log |
| FCN |
HRNetV2p-W48 |
480x480 |
80000 |
- |
- |
45.84 |
47.84 |
model | log |
