Method Details
Details for method 'Global-Local-Refinement'
Method overview
| name | Global-Local-Refinement |
| challenge | pixel-level semantic labeling |
| details | global-residual and local-boundary refinement The method was previously listed as "RefineNet". To avoid confusions with a recently appeared and similarly named approach, the submission name was updated. |
| publication | Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions Rui Zhang, Sheng Tang, Min Lin, Jintao Li, Shuicheng Yan International Joint Conference on Artificial Intelligence (IJCAI) 2017 https://www.ijcai.org/proceedings/2017/479 |
| project page / code | |
| used Cityscapes data | fine annotations |
| used external data | ImageNet |
| runtime | n/a |
| subsampling | no |
| submission date | November, 2016 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 77.2739 |
| iIoU Classes | 53.3869 |
| IoU Categories | 90.0466 |
| iIoU Categories | 76.7731 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 98.6079 | - |
| sidewalk | 86.0874 | - |
| building | 92.8076 | - |
| wall | 57.0287 | - |
| fence | 58.3417 | - |
| pole | 63.2512 | - |
| traffic light | 70.8258 | - |
| traffic sign | 76.7866 | - |
| vegetation | 93.3739 | - |
| terrain | 72.1952 | - |
| sky | 95.3851 | - |
| person | 84.8768 | 65.2578 |
| rider | 67.8724 | 45.2665 |
| car | 95.5686 | 89.1447 |
| truck | 68.5139 | 36.4997 |
| bus | 77.5345 | 50.5457 |
| train | 69.3976 | 42.7489 |
| motorcycle | 65.2388 | 39.4172 |
| bicycle | 74.5106 | 58.2146 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 98.6603 | - |
| nature | 93.0469 | - |
| object | 70.1424 | - |
| sky | 95.3851 | - |
| construction | 93.1054 | - |
| human | 85.2216 | 66.6602 |
| vehicle | 94.7644 | 86.8861 |