Context Encoding for Semantic Segmentation
Introduction
[ALGORITHM]
@InProceedings{Zhang_2018_CVPR,
author = {Zhang, Hang and Dana, Kristin and Shi, Jianping and Zhang, Zhongyue and Wang, Xiaogang and Tyagi, Ambrish and Agrawal, Amit},
title = {Context Encoding for Semantic Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}
Results and models
Cityscapes
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| encnet |
R-50-D8 |
512x1024 |
40000 |
8.6 |
4.58 |
75.67 |
77.08 |
model | log |
| encnet |
R-101-D8 |
512x1024 |
40000 |
12.1 |
2.66 |
75.81 |
77.21 |
model | log |
| encnet |
R-50-D8 |
769x769 |
40000 |
9.8 |
1.82 |
76.24 |
77.85 |
model | log |
| encnet |
R-101-D8 |
769x769 |
40000 |
13.7 |
1.26 |
74.25 |
76.25 |
model | log |
| encnet |
R-50-D8 |
512x1024 |
80000 |
- |
- |
77.94 |
79.13 |
model | log |
| encnet |
R-101-D8 |
512x1024 |
80000 |
- |
- |
78.55 |
79.47 |
model | log |
| encnet |
R-50-D8 |
769x769 |
80000 |
- |
- |
77.44 |
78.72 |
model | log |
| encnet |
R-101-D8 |
769x769 |
80000 |
- |
- |
76.10 |
76.97 |
model | log |
ADE20K
| Method |
Backbone |
Crop Size |
Lr schd |
Mem (GB) |
Inf time (fps) |
mIoU |
mIoU(ms+flip) |
download |
| encnet |
R-50-D8 |
512x512 |
80000 |
10.1 |
22.81 |
39.53 |
41.17 |
model | log |
| encnet |
R-101-D8 |
512x512 |
80000 |
13.6 |
14.87 |
42.11 |
43.61 |
model | log |
| encnet |
R-50-D8 |
512x512 |
160000 |
- |
- |
40.10 |
41.71 |
model | log |
| encnet |
R-101-D8 |
512x512 |
160000 |
- |
- |
42.61 |
44.01 |
model | log |
