Method Details
Details for method 'LiteSeg-Darknet19'
Method overview
| name | LiteSeg-Darknet19 |
| challenge | pixel-level semantic labeling |
| details | |
| publication | LiteSeg: A Litewiegth ConvNet for Semantic Segmentation Taha Emara, Hossam E. Abd El Munim, Hazem M. Abbas DICTA 2019 https://arxiv.org/abs/1912.06683 |
| project page / code | https://github.com/tahaemara/LiteSeg |
| used Cityscapes data | fine annotations, coarse annotations |
| used external data | |
| runtime | 0.0102 s Intel Core i7-8700 @ 3.2GHZ, 16GB memory, and NVIDIA GTX1080Ti GPU card. Input image resolution 360X640. |
| subsampling | no |
| submission date | January, 2019 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 70.7525 |
| iIoU Classes | 49.0959 |
| IoU Categories | 88.2929 |
| iIoU Categories | 76.1058 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 98.0457 | - |
| sidewalk | 82.2171 | - |
| building | 91.332 | - |
| wall | 49.0119 | - |
| fence | 50.8644 | - |
| pole | 58.7912 | - |
| traffic light | 64.3989 | - |
| traffic sign | 72.1014 | - |
| vegetation | 92.6619 | - |
| terrain | 69.4934 | - |
| sky | 94.9922 | - |
| person | 80.7288 | 64.3296 |
| rider | 57.0415 | 40.9096 |
| car | 94.2267 | 88.3481 |
| truck | 49.33 | 29.7104 |
| bus | 61.7539 | 41.146 |
| train | 55.3693 | 35.7465 |
| motorcycle | 53.5775 | 37.0138 |
| bicycle | 68.3589 | 55.5633 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 98.4451 | - |
| nature | 92.3155 | - |
| object | 65.9457 | - |
| sky | 94.9922 | - |
| construction | 91.671 | - |
| human | 81.7301 | 65.8908 |
| vehicle | 92.9506 | 86.3207 |