Details for method 'NV-ADLR'
Method overview
| name |
NV-ADLR |
| challenge |
instance-level semantic labeling |
| details |
NVIDIA Applied Deep Learning Research |
| publication |
Anonymous
|
| project page / code |
|
| used Cityscapes data |
fine annotations |
| used external data |
ImageNet, COCO |
| runtime |
n/a |
| subsampling |
no |
| submission date |
June, 2018 |
| previous submissions |
|
Average results
| Metric |
Value |
| AP | 35.3368 |
| AP50% | 61.5147 |
| AP100m | 49.2773 |
| AP50m | 53.4912 |
Class results
| Class |
AP | AP50% | AP100m | AP50m |
| person | 39.5039 | 73.3105 | 56.658 | 56.7969 |
| rider | 29.4518 | 67.6905 | 42.8494 | 43.748 |
| car | 56.2752 | 81.2474 | 75.2046 | 77.8679 |
| truck | 34.2461 | 46.4058 | 46.6777 | 54.9423 |
| bus | 44.6885 | 61.9192 | 63.1998 | 73.2291 |
| train | 30.3037 | 52.561 | 42.9789 | 54.0974 |
| motorcycle | 27.0827 | 56.8241 | 35.7485 | 36.1995 |
| bicycle | 21.1424 | 52.159 | 30.9017 | 31.0486 |
Links
Download results as .csv file
Benchmark page
