Method Details
Details for method 'AAF+GLR'
Method overview
name | AAF+GLR |
challenge | pixel-level semantic labeling |
details | |
publication | Anonymous |
project page / code | |
used Cityscapes data | fine annotations |
used external data | |
runtime | n/a |
subsampling | no |
submission date | July, 2019 |
previous submissions |
Average results
Metric | Value |
---|---|
IoU Classes | 78.2442 |
iIoU Classes | 54.9269 |
IoU Categories | 90.9473 |
iIoU Categories | 79.3083 |
Class results
Class | IoU | iIoU |
---|---|---|
road | 98.4447 | - |
sidewalk | 84.8036 | - |
building | 92.8368 | - |
wall | 50.845 | - |
fence | 57.7627 | - |
pole | 67.9767 | - |
traffic light | 74.8792 | - |
traffic sign | 78.521 | - |
vegetation | 93.6009 | - |
terrain | 71.5432 | - |
sky | 95.5799 | - |
person | 85.9859 | 68.7674 |
rider | 68.7995 | 48.4963 |
car | 95.8395 | 90.3876 |
truck | 71.3369 | 35.6408 |
bus | 81.8272 | 47.1421 |
train | 74.0087 | 45.8396 |
motorcycle | 66.6573 | 41.1806 |
bicycle | 75.3902 | 61.9606 |
Category results
Category | IoU | iIoU |
---|---|---|
flat | 98.6807 | - |
nature | 93.2621 | - |
object | 73.9127 | - |
sky | 95.5799 | - |
construction | 93.3407 | - |
human | 86.6079 | 70.3478 |
vehicle | 95.2469 | 88.2687 |