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, video
used external data ImageNet, Mapillary
runtime n/a
subsampling no
submission date November, 2022
previous submissions 1, 2, 3, 4

 

Average results

Metric Value
IoU Classes 86.3999
iIoU Classes 71.3436
IoU Categories 93.1859
iIoU Categories 84.4625

 

Class results

Class IoU iIoU
road 98.9194 -
sidewalk 89.2296 -
building 95.0222 -
wall 74.63 -
fence 72.5776 -
pole 76.2953 -
traffic light 82.0825 -
traffic sign 84.8163 -
vegetation 94.5552 -
terrain 75.1585 -
sky 96.333 -
person 90.0081 77.2739
rider 80.4667 63.3365
car 96.764 91.8529
truck 84.8885 62.5307
bus 95.3242 72.3125
train 93.4997 69.0724
motorcycle 78.8193 64.4262
bicycle 82.2088 69.9439

 

Category results

Category IoU iIoU
flat 98.8531 -
nature 94.3218 -
object 81.0424 -
sky 96.333 -
construction 95.0894 -
human 90.125 78.1166
vehicle 96.5368 90.8084

 

Links

Download results as .csv file

Benchmark page