Details for method 'AdapNetv2_ROB'
Method overview
| name |
AdapNetv2_ROB |
| challenge |
pixel-level semantic labeling |
| details |
|
| publication |
Anonymous
|
| project page / code |
|
| used Cityscapes data |
fine annotations |
| used external data |
ImageNet |
| runtime |
n/a |
| subsampling |
no |
| submission date |
June, 2018 |
| previous submissions |
|
Average results
| Metric |
Value |
| IoU Classes | 63.7569 |
| iIoU Classes | 34.9221 |
| IoU Categories | 84.2818 |
| iIoU Categories | 62.4002 |
Class results
| Class |
IoU |
iIoU |
| road | 97.614 | - |
| sidewalk | 79.1546 | - |
| building | 88.7351 | - |
| wall | 37.8351 | - |
| fence | 33.0608 | - |
| pole | 48.2792 | - |
| traffic light | 50.1136 | - |
| traffic sign | 59.0733 | - |
| vegetation | 89.9746 | - |
| terrain | 67.0356 | - |
| sky | 93.8044 | - |
| person | 73.5049 | 42.8935 |
| rider | 50.5188 | 23.7107 |
| car | 92.4224 | 83.527 |
| truck | 46.323 | 18.4356 |
| bus | 58.4978 | 31.6116 |
| train | 42.9393 | 17.0481 |
| motorcycle | 42.5657 | 21.6881 |
| bicycle | 59.9282 | 40.4622 |
Category results
| Category |
IoU |
iIoU |
| flat | 98.184 | - |
| nature | 89.9833 | - |
| object | 53.9368 | - |
| sky | 93.8044 | - |
| construction | 88.7993 | - |
| human | 74.0933 | 44.315 |
| vehicle | 91.1716 | 80.4853 |
Links
Download results as .csv file
Benchmark page
