Details for method 'PolyTransform + SegFix + BPR'
Method overview
| name |
PolyTransform + SegFix + BPR |
| challenge |
instance-level semantic labeling |
| details |
Anonymous CVPR 2021 submission #4697 |
| publication |
Anonymous
|
| project page / code |
|
| used Cityscapes data |
fine annotations |
| used external data |
ImageNet, COCO |
| runtime |
n/a |
| subsampling |
no |
| submission date |
November, 2020 |
| previous submissions |
|
Average results
| Metric |
Value |
| AP | 42.6512 |
| AP50% | 66.5055 |
| AP100m | 57.4983 |
| AP50m | 60.7325 |
Class results
| Class |
AP | AP50% | AP100m | AP50m |
| person | 46.0349 | 76.9908 | 63.3646 | 63.4898 |
| rider | 37.1066 | 72.3817 | 51.5779 | 52.2112 |
| car | 62.7507 | 83.7732 | 81.1229 | 83.6874 |
| truck | 41.2719 | 52.6667 | 55.8305 | 64.2081 |
| bus | 52.6533 | 68.5697 | 70.9607 | 77.7261 |
| train | 43.7216 | 63.3475 | 59.933 | 66.5914 |
| motorcycle | 32.6051 | 59.413 | 41.9452 | 42.6975 |
| bicycle | 25.0652 | 54.9011 | 35.2521 | 35.2482 |
Links
Download results as .csv file
Benchmark page
