Method Details
Details for method 'Boundary-aware Instance Segmentation'
Method overview
| name | Boundary-aware Instance Segmentation |
| challenge | instance-level semantic labeling |
| details | End-to-end model for instance segmentation using VGG16 network Previously listed as "Shape-Aware Instance Segmentation" |
| publication | Boundary-aware Instance Segmentation Zeeshan Hayder, Xuming He, Mathieu Salzmann CVPR 2017 https://arxiv.org/abs/1612.03129 |
| project page / code | |
| used Cityscapes data | fine annotations |
| used external data | |
| runtime | n/a |
| subsampling | 2 |
| submission date | November, 2016 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| AP | 17.4429 |
| AP50% | 36.698 |
| AP100m | 29.2624 |
| AP50m | 34.0217 |
Class results
| Class | AP | AP50% | AP100m | AP50m |
|---|---|---|---|---|
| person | 14.5862 | 34.0371 | 30.2717 | 31.5085 |
| rider | 12.9139 | 40.3576 | 22.6874 | 23.4083 |
| car | 35.6633 | 54.7155 | 58.1578 | 63.1401 |
| truck | 16.0397 | 27.2346 | 24.928 | 32.1511 |
| bus | 23.2125 | 40.1074 | 38.616 | 50.4875 |
| train | 18.9998 | 38.8648 | 29.9035 | 40.4208 |
| motorcycle | 10.3348 | 32.2395 | 15.2576 | 16.4528 |
| bicycle | 7.79321 | 26.0274 | 14.2769 | 14.6046 |