Details for method 'NV-ADLR'
Method overview
| name |
NV-ADLR |
| challenge |
pixel-level semantic labeling |
| details |
NVIDIA Applied Deep Learning Research |
| publication |
Anonymous
|
| project page / code |
|
| used Cityscapes data |
fine annotations, coarse annotations |
| used external data |
Mapillary |
| runtime |
n/a |
| subsampling |
no |
| submission date |
May, 2018 |
| previous submissions |
1, 2 |
Average results
| Metric |
Value |
| IoU Classes | 83.1794 |
| iIoU Classes | 64.1599 |
| IoU Categories | 92.1397 |
| iIoU Categories | 82.2344 |
Class results
| Class |
IoU |
iIoU |
| road | 98.7417 | - |
| sidewalk | 87.5657 | - |
| building | 94.0524 | - |
| wall | 63.5195 | - |
| fence | 66.6868 | - |
| pole | 71.9888 | - |
| traffic light | 78.7993 | - |
| traffic sign | 82.3801 | - |
| vegetation | 94.2709 | - |
| terrain | 75.26 | - |
| sky | 96.069 | - |
| person | 87.8162 | 72.764 |
| rider | 73.2647 | 52.3703 |
| car | 96.4122 | 92.3937 |
| truck | 78.8809 | 51.83 |
| bus | 93.0303 | 63.876 |
| train | 90.414 | 58.3185 |
| motorcycle | 72.699 | 54.3973 |
| bicycle | 78.5564 | 67.3291 |
Category results
| Category |
IoU |
iIoU |
| flat | 98.8275 | - |
| nature | 93.9764 | - |
| object | 77.6013 | - |
| sky | 96.069 | - |
| construction | 94.363 | - |
| human | 88.0302 | 73.572 |
| vehicle | 96.1104 | 90.8967 |
Links
Download results as .csv file
Benchmark page
