Method Details
Details for method 'Roadstar.ai_CV(SFNet)'
Method overview
| name | Roadstar.ai_CV(SFNet) |
| challenge | pixel-level semantic labeling |
| details | based on only fine labels, with focus on the loss distribution |
| publication | Roadstar.ai-CV Maosheng Ye, Guang Zhou, Tongyi Cao, YongTao Huang, Yinzi Chen |
| project page / code | |
| used Cityscapes data | fine annotations |
| used external data | |
| runtime | 0.2 s gtx1080ti |
| subsampling | no |
| submission date | November, 2017 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 78.1742 |
| iIoU Classes | 58.4077 |
| IoU Categories | 90.7814 |
| iIoU Categories | 81.9928 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 98.3805 | - |
| sidewalk | 85.2897 | - |
| building | 92.8261 | - |
| wall | 56.0476 | - |
| fence | 58.7211 | - |
| pole | 67.5674 | - |
| traffic light | 76.1626 | - |
| traffic sign | 79.1766 | - |
| vegetation | 93.5749 | - |
| terrain | 72.3615 | - |
| sky | 95.0279 | - |
| person | 86.3156 | 74.6243 |
| rider | 73.0405 | 51.7704 |
| car | 95.6341 | 90.1974 |
| truck | 65.8679 | 42.8367 |
| bus | 77.8583 | 54.0192 |
| train | 65.5991 | 39.3991 |
| motorcycle | 69.1349 | 48.3283 |
| bicycle | 76.723 | 66.0866 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 98.622 | - |
| nature | 93.2601 | - |
| object | 73.7051 | - |
| sky | 95.0279 | - |
| construction | 93.2852 | - |
| human | 86.5434 | 75.4057 |
| vehicle | 95.0261 | 88.58 |