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 September, 2016
previous submissions

 

Average results

Metric Value
IoU Classes 77.2923
iIoU Classes 52.2831
IoU Categories 89.7412
iIoU Categories 75.0958

 

Class results

Class IoU iIoU
road 98.4352 -
sidewalk 85.0499 -
building 92.3978 -
wall 54.5957 -
fence 54.3185 -
pole 62.6863 -
traffic light 71.2731 -
traffic sign 76.4089 -
vegetation 93.2521 -
terrain 71.6831 -
sky 94.7487 -
person 84.2041 62.7498
rider 66.5005 42.612
car 95.287 88.2232
truck 67.4406 34.585
bus 84.7757 49.4037
train 77.129 45.9866
motorcycle 64.8009 38.9724
bicycle 73.566 55.7318

 

Category results

Category IoU iIoU
flat 98.578 -
nature 92.8817 -
object 69.9173 -
sky 94.7487 -
construction 92.82 -
human 84.5569 64.1698
vehicle 94.6854 86.0218

 

Links

Download results as .csv file

Benchmark page