Method Details


Details for method 'MeiTuan-BaseModel'

 

Method overview

name MeiTuan-BaseModel
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 July, 2022
previous submissions

 

Average results

Metric Value
IoU Classes 86.4602
iIoU Classes 73.1928
IoU Categories 93.3677
iIoU Categories 85.3627

 

Class results

Class IoU iIoU
road 98.9586 -
sidewalk 89.6034 -
building 95.0695 -
wall 73.5219 -
fence 72.6057 -
pole 76.7045 -
traffic light 82.1836 -
traffic sign 85.2702 -
vegetation 94.6503 -
terrain 75.6262 -
sky 96.3526 -
person 90.6267 78.879
rider 80.9148 65.7989
car 96.8486 91.7284
truck 84.4521 62.3626
bus 95.4648 74.7988
train 92.3863 72.8257
motorcycle 78.8267 65.8625
bicycle 82.6766 73.2863

 

Category results

Category IoU iIoU
flat 98.9207 -
nature 94.472 -
object 81.4125 -
sky 96.3526 -
construction 95.1907 -
human 90.5974 79.7234
vehicle 96.6281 91.002

 

Links

Download results as .csv file

Benchmark page