Dynamic Multi-scale Filters for Semantic Segmentation
Introduction
[ALGORITHM]
@InProceedings{He_2019_ICCV,
author = {He, Junjun and Deng, Zhongying and Qiao, Yu},
title = {Dynamic Multi-Scale Filters for Semantic Segmentation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}
Results and models
Cityscapes
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| DMNet |
R-50-D8 |
512x1024 |
40000 |
7.0 |
3.66 |
77.78 |
79.14 |
model | log |
| DMNet |
R-101-D8 |
512x1024 |
40000 |
10.6 |
2.54 |
78.37 |
79.72 |
model | log |
| DMNet |
R-50-D8 |
769x769 |
40000 |
7.9 |
1.57 |
78.49 |
80.27 |
model | log |
| DMNet |
R-101-D8 |
769x769 |
40000 |
12.0 |
1.01 |
77.62 |
78.94 |
model | log |
| DMNet |
R-50-D8 |
512x1024 |
80000 |
- |
- |
79.07 |
80.22 |
model | log |
| DMNet |
R-101-D8 |
512x1024 |
80000 |
- |
- |
79.64 |
80.67 |
model | log |
| DMNet |
R-50-D8 |
769x769 |
80000 |
- |
- |
79.22 |
80.55 |
model | log |
| DMNet |
R-101-D8 |
769x769 |
80000 |
- |
- |
79.19 |
80.65 |
model | log |
ADE20K
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| DMNet |
R-50-D8 |
512x512 |
80000 |
9.4 |
20.95 |
42.37 |
43.62 |
model | log |
| DMNet |
R-101-D8 |
512x512 |
80000 |
13.0 |
13.88 |
45.34 |
46.13 |
model | log |
| DMNet |
R-50-D8 |
512x512 |
160000 |
- |
- |
43.15 |
44.17 |
model | log |
| DMNet |
R-101-D8 |
512x512 |
160000 |
- |
- |
45.42 |
46.76 |
model | log |
