Method Details
Details for method 'Pixel-level Encoding for Instance Segmentation'
Method overview
| name | Pixel-level Encoding for Instance Segmentation |
| challenge | instance-level semantic labeling |
| details | We predict three encoding channels from a single image using an FCN: semantic labels, depth classes, and an instance-aware representation based on directions towards instance centers. Using low-level computer vision techniques, we obtain pixel-level and instance-level semantic labeling paired with a depth estimate of the instances. |
| publication | Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling J. Uhrig, M. Cordts, U. Franke, and T. Brox GCPR 2016 http://arxiv.org/abs/1604.05096 |
| project page / code | |
| used Cityscapes data | fine annotations, stereo |
| used external data | ImageNet |
| runtime | n/a |
| subsampling | no |
| submission date | April, 2016 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| AP | 8.89385 |
| AP50% | 21.1405 |
| AP100m | 15.2578 |
| AP50m | 16.7142 |
Class results
| Class | AP | AP50% | AP100m | AP50m |
|---|---|---|---|---|
| person | 12.5394 | 31.8091 | 24.383 | 24.9723 |
| rider | 11.6934 | 33.8132 | 20.2862 | 20.96 |
| car | 22.4908 | 37.8369 | 36.4126 | 40.7182 |
| truck | 3.25894 | 7.56638 | 5.52384 | 6.72277 |
| bus | 5.86555 | 11.9891 | 10.5666 | 13.4667 |
| train | 3.22664 | 8.48319 | 5.17961 | 6.38073 |
| motorcycle | 6.92793 | 20.4522 | 10.5089 | 11.1971 |
| bicycle | 5.14812 | 17.1742 | 9.2017 | 9.29596 |