Method Details
Details for method 'seamseg_rvcsubset'
Method overview
| name | seamseg_rvcsubset |
| challenge | instance-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 |
|---|---|
| AP | 22.103 |
| AP50% | 39.3638 |
| AP100m | 31.2186 |
| AP50m | 32.0726 |
Class results
| Class | AP | AP50% | AP100m | AP50m |
|---|---|---|---|---|
| person | 27.1264 | 52.5923 | 40.5091 | 40.0111 |
| rider | 18.0369 | 40.7078 | 27.4612 | 27.2168 |
| car | 37.5172 | 55.3591 | 53.172 | 53.6773 |
| truck | 26.4434 | 37.2056 | 33.226 | 33.3308 |
| bus | 30.3537 | 44.1843 | 41.6622 | 41.8183 |
| train | 9.83871 | 17.817 | 15.608 | 23.2576 |
| motorcycle | 15.8103 | 36.6972 | 19.8369 | 19.2293 |
| bicycle | 11.6973 | 30.3469 | 18.2735 | 18.0396 |