Method Details
Details for method 'm-TCFs'
Method overview
| name | m-TCFs |
| challenge | pixel-level semantic labeling |
| details | Convolutional Neural Network |
| publication | Anonymous |
| project page / code | |
| used Cityscapes data | fine annotations, coarse annotations |
| used external data | ImageNet |
| runtime | 1 s NVIDIA Titan X |
| subsampling | no |
| submission date | May, 2016 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 71.7567 |
| iIoU Classes | 43.5631 |
| IoU Categories | 87.5623 |
| iIoU Categories | 70.5543 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 98.2327 | - |
| sidewalk | 83.6283 | - |
| building | 91.1948 | - |
| wall | 48.3739 | - |
| fence | 53.1691 | - |
| pole | 55.8225 | - |
| traffic light | 64.2509 | - |
| traffic sign | 70.2568 | - |
| vegetation | 92.2337 | - |
| terrain | 70.2284 | - |
| sky | 94.468 | - |
| person | 79.9345 | 55.8028 |
| rider | 59.1749 | 33.6008 |
| car | 94.066 | 86.575 |
| truck | 55.9801 | 24.8357 |
| bus | 69.0838 | 36.5268 |
| train | 58.1794 | 31.9241 |
| motorcycle | 56.6571 | 30.4697 |
| bicycle | 68.4413 | 48.7696 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 98.4198 | - |
| nature | 91.9018 | - |
| object | 63.2134 | - |
| sky | 94.468 | - |
| construction | 91.455 | - |
| human | 80.3144 | 57.0283 |
| vehicle | 93.1636 | 84.0804 |