Method Details


Details for method 'MIX6D_RVC'

 

Method overview

name MIX6D_RVC
challenge pixel-level semantic labeling
details MIX6D_RVC
publication Anonymous
project page / code
used Cityscapes data fine annotations
used external data ImageNet, SCANNET, VIPER, MVD, ADE20K, Wilddash
runtime n/a
subsampling no
submission date October, 2022
previous submissions 1, 2

 

Average results

Metric Value
IoU Classes 79.7789
iIoU Classes 58.6198
IoU Categories 89.3021
iIoU Categories 74.6083

 

Class results

Class IoU iIoU
road 98.0501 -
sidewalk 82.5428 -
building 92.6061 -
wall 61.8621 -
fence 62.2944 -
pole 61.6636 -
traffic light 70.7902 -
traffic sign 74.6697 -
vegetation 93.1099 -
terrain 69.5533 -
sky 94.9686 -
person 84.3718 64.127
rider 68.888 45.145
car 95.0283 86.0258
truck 78.3986 45.915
bus 92.2993 58.2352
train 90.6228 63.882
motorcycle 69.6393 46.7418
bicycle 74.4407 58.8867

 

Category results

Category IoU iIoU
flat 97.7341 -
nature 92.6299 -
object 68.27 -
sky 94.9686 -
construction 92.393 -
human 84.6776 65.0164
vehicle 94.4417 84.2002

 

Links

Download results as .csv file

Benchmark page