Method Details
Details for method 'DPN'
Method overview
| name | DPN |
| challenge | pixel-level semantic labeling |
| details | Trained on a pre-release version of the dataset |
| publication | Semantic Image Segmentation via Deep Parsing Network Z. Liu, X. Li, P. Luo, C. C. Loy, and X. Tang ICCV 2015 http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Liu_Semantic_Image_Segmentation_ICCV_2015_paper.pdf |
| project page / code | |
| used Cityscapes data | fine annotations, coarse annotations |
| used external data | ImageNet |
| runtime | n/a |
| subsampling | 3 |
| submission date | April, 2016 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 59.0758 |
| iIoU Classes | 28.0994 |
| IoU Categories | 79.5125 |
| iIoU Categories | 57.9467 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 96.3475 | - |
| sidewalk | 71.7161 | - |
| building | 86.7143 | - |
| wall | 43.7101 | - |
| fence | 31.7236 | - |
| pole | 29.2457 | - |
| traffic light | 35.7918 | - |
| traffic sign | 47.4143 | - |
| vegetation | 88.4296 | - |
| terrain | 63.1326 | - |
| sky | 93.8724 | - |
| person | 64.7061 | 38.9061 |
| rider | 38.6911 | 12.7788 |
| car | 88.8495 | 78.5546 |
| truck | 47.995 | 13.4423 |
| bus | 56.425 | 24.0482 |
| train | 49.3935 | 19.1641 |
| motorcycle | 38.2506 | 10.7 |
| bicycle | 50.0309 | 27.2009 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 97.345 | - |
| nature | 88.0022 | - |
| object | 37.7337 | - |
| sky | 93.8724 | - |
| construction | 86.5834 | - |
| human | 65.3945 | 39.906 |
| vehicle | 87.6566 | 75.9874 |