Method Details


Details for method 'AntGroup-AI-VisionAlgo'

 

Method overview

name AntGroup-AI-VisionAlgo
challenge pixel-level semantic labeling
details AntGroup AI vision algo
publication Anonymous
project page / code
used Cityscapes data fine annotations, coarse annotations
used external data ImageNet, Mapillary
runtime n/a
subsampling no
submission date September, 2020
previous submissions 1

 

Average results

Metric Value
IoU Classes 85.5031
iIoU Classes 69.6408
IoU Categories 93.0423
iIoU Categories 84.4123

 

Class results

Class IoU iIoU
road 98.9226 -
sidewalk 89.0208 -
building 94.7793 -
wall 70.9382 -
fence 70.5274 -
pole 75.079 -
traffic light 81.5173 -
traffic sign 84.4057 -
vegetation 94.5403 -
terrain 75.0161 -
sky 96.2866 -
person 90.0316 77.1549
rider 78.9868 61.6942
car 96.7972 91.9355
truck 82.8967 60.2196
bus 94.4977 71.2336
train 91.258 61.8362
motorcycle 77.3708 61.5895
bicycle 81.6869 71.4632

 

Category results

Category IoU iIoU
flat 98.8716 -
nature 94.2768 -
object 80.1896 -
sky 96.2866 -
construction 95.003 -
human 90.0691 77.8932
vehicle 96.5997 90.9313

 

Links

Download results as .csv file

Benchmark page