Details for method 'SRC-B-MachineLearningLab'
Method overview
| name |
SRC-B-MachineLearningLab |
| challenge |
pixel-level semantic labeling |
| details |
Samsung Research Center MachineLearningLab. The result is tested by multi scale and filp. The paper is in preparing. |
| publication |
Jianlong Yuan, Zelu Deng, Shu Wang, Zhenbo Luo
|
| project page / code |
|
| used Cityscapes data |
fine annotations, coarse annotations |
| used external data |
ImageNet |
| runtime |
n/a |
| subsampling |
no |
| submission date |
August, 2018 |
| previous submissions |
|
Average results
| Metric |
Value |
| IoU Classes | 82.4876 |
| iIoU Classes | 60.6631 |
| IoU Categories | 91.8136 |
| iIoU Categories | 81.4875 |
Class results
| Class |
IoU |
iIoU |
| road | 98.7264 | - |
| sidewalk | 87.2914 | - |
| building | 94.0168 | - |
| wall | 64.8086 | - |
| fence | 64.4752 | - |
| pole | 70.7068 | - |
| traffic light | 76.7335 | - |
| traffic sign | 81.2206 | - |
| vegetation | 93.9585 | - |
| terrain | 73.8663 | - |
| sky | 95.8668 | - |
| person | 87.8758 | 72.8885 |
| rider | 72.6575 | 51.39 |
| car | 96.2573 | 91.0492 |
| truck | 79.2042 | 44.2228 |
| bus | 92.1619 | 57.027 |
| train | 88.1155 | 53.8644 |
| motorcycle | 71.5498 | 49.5469 |
| bicycle | 77.7714 | 65.3157 |
Category results
| Category |
IoU |
iIoU |
| flat | 98.7833 | - |
| nature | 93.6873 | - |
| object | 76.4173 | - |
| sky | 95.8668 | - |
| construction | 94.1364 | - |
| human | 87.8805 | 73.7331 |
| vehicle | 95.9233 | 89.242 |
Links
Download results as .csv file
Benchmark page
