Method Details


Details for method 'JSU_IDT_group'

 

Method overview

name JSU_IDT_group
challenge pixel-level semantic labeling
details
publication Anonymous
project page / code
used Cityscapes data fine annotations
used external data ImageNet
runtime n/a
subsampling no
submission date January, 2022
previous submissions

 

Average results

Metric Value
IoU Classes 85.8667
iIoU Classes 69.0301
IoU Categories 93.1585
iIoU Categories 84.7639

 

Class results

Class IoU iIoU
road 98.9975 -
sidewalk 89.4421 -
building 94.881 -
wall 73.126 -
fence 69.1677 -
pole 75.6851 -
traffic light 82.1686 -
traffic sign 85.0499 -
vegetation 94.4899 -
terrain 75.8745 -
sky 96.3034 -
person 90.0583 77.4795
rider 79.3188 63.2564
car 97.0099 92.3638
truck 83.7241 48.1885
bus 94.9399 73.9745
train 92.3479 63.456
motorcycle 77.3525 61.618
bicycle 81.5298 71.904

 

Category results

Category IoU iIoU
flat 98.9375 -
nature 94.3482 -
object 80.6847 -
sky 96.3034 -
construction 94.9576 -
human 90.1635 78.4475
vehicle 96.7142 91.0802

 

Links

Download results as .csv file

Benchmark page