Method Details


Details for method 'TuSimple_Coarse'

 

Method overview

name TuSimple_Coarse
challenge pixel-level semantic labeling
details
publication Anonymous
project page / code
used Cityscapes data fine annotations, coarse annotations
used external data ImageNet
runtime n/a
subsampling no
submission date November, 2016
previous submissions 1, 2, 3

 

Average results

Metric Value
IoU Classes 78.4742
iIoU Classes 54.9181
IoU Categories 90.1758
iIoU Categories 75.1856

 

Class results

Class IoU iIoU
road 98.4659 -
sidewalk 85.5067 -
building 92.7892 -
wall 58.1437 -
fence 56.0147 -
pole 65.0951 -
traffic light 73.4641 -
traffic sign 77.9632 -
vegetation 93.2967 -
terrain 72.0241 -
sky 95.2038 -
person 84.7836 62.6574
rider 68.5181 43.8829
car 95.3888 88.145
truck 69.7884 38.2362
bus 84.7451 52.4678
train 79.981 49.2899
motorcycle 65.9795 43.2427
bicycle 73.8583 61.4227

 

Category results

Category IoU iIoU
flat 98.587 -
nature 92.9983 -
object 71.9739 -
sky 95.2038 -
construction 93.0328 -
human 84.7821 63.8945
vehicle 94.6526 86.4768

 

Links

Download results as .csv file

Benchmark page