Method Details


Details for method 'NetWarp'

 

Method overview

name NetWarp
challenge pixel-level semantic labeling
details
publication Anonymous
project page / code
used Cityscapes data fine annotations, coarse annotations, video
used external data ImageNet
runtime n/a
subsampling no
submission date March, 2017
previous submissions

 

Average results

Metric Value
IoU Classes 80.4624
iIoU Classes 59.541
IoU Categories 91.0409
iIoU Categories 79.7891

 

Class results

Class IoU iIoU
road 98.6427 -
sidewalk 86.7088 -
building 93.3647 -
wall 60.5863 -
fence 62.5754 -
pole 68.5744 -
traffic light 75.8983 -
traffic sign 79.9821 -
vegetation 93.5107 -
terrain 72.017 -
sky 95.2658 -
person 86.5258 69.7358
rider 72.0742 52.3138
car 95.8845 90.7608
truck 72.9361 41.892
bus 89.9477 55.6941
train 77.353 52.7236
motorcycle 70.4942 51.4052
bicycle 76.4434 61.8032

 

Category results

Category IoU iIoU
flat 98.6303 -
nature 93.1984 -
object 74.7951 -
sky 95.2658 -
construction 93.5439 -
human 86.5642 70.7129
vehicle 95.2888 88.8652

 

Links

Download results as .csv file

Benchmark page