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 November, 2020
previous submissions 1, 2

 

Average results

Metric Value
IoU Classes 85.6998
iIoU Classes 69.9863
IoU Categories 93.1833
iIoU Categories 84.7984

 

Class results

Class IoU iIoU
road 98.9323 -
sidewalk 89.1793 -
building 94.8695 -
wall 71.0241 -
fence 70.7663 -
pole 76.127 -
traffic light 81.9711 -
traffic sign 84.7389 -
vegetation 94.6166 -
terrain 75.1552 -
sky 96.347 -
person 90.0844 77.5177
rider 79.3404 62.4148
car 96.7815 92.4305
truck 83.0014 60.6407
bus 94.6174 71.7778
train 91.2785 61.893
motorcycle 77.548 61.5168
bicycle 81.9168 71.699

 

Category results

Category IoU iIoU
flat 98.8728 -
nature 94.3491 -
object 80.8708 -
sky 96.347 -
construction 95.0852 -
human 90.1564 78.2483
vehicle 96.6014 91.3486

 

Links

Download results as .csv file

Benchmark page