Method Details
Details for method 'PANet [fine-only]'
Method overview
| name | PANet [fine-only] |
| challenge | instance-level semantic labeling |
| details | PANet, ResNet-50 as base model, Cityscapes fine-only, training hyper-parameters are adopted from Mask R-CNN. |
| publication | Path Aggregation Network for Instance Segmentation Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, Jiaya Jia CVPR 2018 https://arxiv.org/abs/1803.01534 |
| project page / code | https://github.com/ShuLiu1993/PANet |
| used Cityscapes data | fine annotations |
| used external data | ImageNet |
| runtime | n/a |
| subsampling | no |
| submission date | November, 2017 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| AP | 31.7749 |
| AP50% | 57.1443 |
| AP100m | 44.2493 |
| AP50m | 45.9617 |
Class results
| Class | AP | AP50% | AP100m | AP50m |
|---|---|---|---|---|
| person | 36.8099 | 68.205 | 53.8773 | 53.6993 |
| rider | 30.3681 | 66.3039 | 43.25 | 43.4954 |
| car | 54.7605 | 78.4773 | 73.3949 | 75.4808 |
| truck | 27.0499 | 38.6756 | 37.2238 | 40.138 |
| bus | 36.325 | 55.1511 | 50.6716 | 56.215 |
| train | 25.5452 | 48.4891 | 35.9887 | 38.9501 |
| motorcycle | 22.5798 | 51.9109 | 29.0128 | 29.5473 |
| bicycle | 20.7608 | 49.9416 | 30.5755 | 30.1679 |