Method Details


Details for method 'UDSSEG_RVC'

 

Method overview

name UDSSEG_RVC
challenge pixel-level semantic labeling
details UDSSEG_RVC
publication Anonymous
project page / code
used Cityscapes data fine annotations
used external data scannet, ade, viper, ade, mapillary
runtime n/a
subsampling no
submission date September, 2022
previous submissions

 

Average results

Metric Value
IoU Classes 79.4296
iIoU Classes 55.9052
IoU Categories 90.7117
iIoU Categories 77.1148

 

Class results

Class IoU iIoU
road 98.3547 -
sidewalk 86.6773 -
building 93.4131 -
wall 63.4146 -
fence 64.5392 -
pole 67.3385 -
traffic light 73.5911 -
traffic sign 76.878 -
vegetation 93.6881 -
terrain 72.4324 -
sky 95.9016 -
person 85.0632 64.9014
rider 67.9307 42.657
car 95.8798 89.9238
truck 73.3767 45.3524
bus 83.5866 55.0277
train 77.0794 50.2419
motorcycle 65.973 42.4772
bicycle 74.044 56.6603

 

Category results

Category IoU iIoU
flat 98.2686 -
nature 93.3481 -
object 73.0353 -
sky 95.9016 -
construction 93.6949 -
human 85.4753 66.2153
vehicle 95.2584 88.0144

 

Links

Download results as .csv file

Benchmark page