- Submitted by
- Oliver Zendel
- Authors
- Porzi, Lorenzo and Rota Bulò, Samuel and Colovic, Aleksander and Kontschieder, Peter
- Venue
- The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
- Abstract
- 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); Trained and Submitted by Oliver Zendel for RVC
- Runtime
- 500 ms
- External data used
- model pre-trained on ImageNet; regular training on altered MVD to contain WildDash2 labels (van, pickup) (20k frames) no other dataset (i.e. no VIPER frames)
- Links
-
- Number of submissions
- 1
- Detailed results
-
| Class |
IoU (day) |
IoU (sunset) |
IoU (rain) |
IoU (snow) |
IoU (night) |
IoU (mean) |
| Sky | 93.5 | 92.5 | 87.2 | 87.5 | 50.6 | 82.3 |
| Road | 77.4 | 83.4 | 92.2 | 87.5 | 83.4 | 84.8 |
| Sidewalk | 66.0 | 59.2 | 49.1 | 56.3 | 46.2 | 55.3 |
| Terrain | 47.2 | 60.5 | 15.3 | 29.9 | 39.6 | 38.5 |
| Tree | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| Vegetation | 22.6 | 13.8 | 25.5 | 20.4 | 15.5 | 19.6 |
| Building | 77.2 | 71.9 | 66.5 | 73.3 | 56.1 | 69.0 |
| Infrastructure | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| Fence | 26.3 | 21.1 | 14.6 | 16.9 | 14.1 | 18.6 |
| Billboard | 32.5 | 29.1 | 31.7 | 23.4 | 30.4 | 29.4 |
| Trafficlight | 69.1 | 65.9 | 72.3 | 76.4 | 58.8 | 68.5 |
| Trafficsign | 23.7 | 62.1 | 67.8 | 27.1 | 65.6 | 49.2 |
| Mobilebarrier | 0.1 | 0.1 | 0.2 | 0.0 | 0.0 | 0.1 |
| Firehydrant | 52.3 | 47.1 | 66.2 | 72.6 | 61.3 | 59.9 |
| Chair | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| Trash | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| Trashcan | 52.8 | 26.7 | 27.7 | 41.5 | 37.3 | 37.2 |
| Person | 74.7 | 48.2 | 59.1 | 72.1 | 59.1 | 62.6 |
| Motorcycle | 4.0 | 18.1 | 29.1 | 38.0 | 17.7 | 21.4 |
| Car | 53.0 | 44.6 | 55.9 | 53.1 | 39.3 | 49.2 |
| Van | 40.3 | 0.9 | 18.1 | 9.9 | 0.0 | 13.8 |
| Bus | 16.2 | 23.2 | 13.6 | 3.5 | 23.1 | 15.9 |
| Truck | 72.1 | 58.2 | 57.7 | 60.2 | 26.5 | 54.9 |
| Mean | 39.2 | 35.9 | 37.0 | 36.9 | 31.5 | 36.1 |