Details for method 'Deep Watershed Transformation'
Method overview
| name |
Deep Watershed Transformation |
| challenge |
instance-level semantic labeling |
| details |
|
| publication |
Anonymous
|
| project page / code |
|
| used Cityscapes data |
fine annotations |
| used external data |
ImageNet |
| runtime |
n/a |
| subsampling |
2 |
| submission date |
November, 2016 |
| previous submissions |
|
Average results
| Metric |
Value |
| AP | 15.069 |
| AP50% | 29.5369 |
| AP100m | 25.3539 |
| AP50m | 30.7045 |
Class results
| Class |
AP | AP50% | AP100m | AP50m |
| person | 14.6503 | 33.0537 | 26.3622 | 26.2866 |
| rider | 12.452 | 33.7511 | 21.0643 | 21.4455 |
| car | 29.8197 | 46.8796 | 48.1299 | 52.0001 |
| truck | 15.5879 | 24.6358 | 26.4813 | 36.3093 |
| bus | 19.9576 | 31.3615 | 36.0142 | 50.8475 |
| train | 14.6826 | 27.1403 | 24.6282 | 37.4012 |
| motorcycle | 8.18701 | 23.0541 | 11.9788 | 12.909 |
| bicycle | 5.21514 | 16.4194 | 8.17176 | 8.43647 |
Links
Download results as .csv file
Benchmark page
