Method Details
Details for method 'seamseg_rvcsubset'
Method overview
| name | seamseg_rvcsubset |
| challenge | pixel-level semantic labeling |
| details | Seamless Scene Segmentation Resnet101, pretrained on Imagenet; supplied with altered MVD to include WildDash2 classes; does not contain other RVC label policies (i.e. no ADE20K/COCO-specific classes -> rvcsubset and not a proper submission) |
| publication | Seamless Scene Segmentation Porzi, Lorenzo and Rota Bulò, Samuel and Colovic, Aleksander and Kontschieder, Peter The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 https://arxiv.org/abs/1905.01220 |
| project page / code | https://github.com/mapillary/seamseg |
| used Cityscapes data | |
| used external data | model pre-trained on ImageNet; regular training on altered MVD to contain WildDash2 labels (van, pickup) (20k frames) no other dataset (i.e. no Cityscapes frames) |
| runtime | n/a |
| subsampling | no |
| submission date | August, 2020 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 66.9732 |
| iIoU Classes | 44.8029 |
| IoU Categories | 86.041 |
| iIoU Categories | 67.9389 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 87.7048 | - |
| sidewalk | 72.9796 | - |
| building | 90.3207 | - |
| wall | 47.7361 | - |
| fence | 49.9017 | - |
| pole | 64.0589 | - |
| traffic light | 71.2021 | - |
| traffic sign | 71.086 | - |
| vegetation | 92.4123 | - |
| terrain | 52.6922 | - |
| sky | 94.7661 | - |
| person | 79.3465 | 57.6053 |
| rider | 45.03 | 34.1649 |
| car | 87.5168 | 77.2152 |
| truck | 53.4387 | 39.9525 |
| bus | 69.3044 | 46.4225 |
| train | 36.7389 | 21.9647 |
| motorcycle | 46.9271 | 39.5278 |
| bicycle | 59.3287 | 41.5706 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 88.8997 | - |
| nature | 91.3352 | - |
| object | 68.7446 | - |
| sky | 94.7661 | - |
| construction | 89.7934 | - |
| human | 82.38 | 60.8442 |
| vehicle | 86.3683 | 75.0336 |