Method Details


Details for method 'iFLYTEK-CV'

 

Method overview

name iFLYTEK-CV
challenge pixel-level semantic labeling
details iFLYTEK Research, CV Group
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, 2019
previous submissions 1, 2

 

Average results

Metric Value
IoU Classes 84.4431
iIoU Classes 64.9429
IoU Categories 92.4444
iIoU Categories 82.3887

 

Class results

Class IoU iIoU
road 98.8999 -
sidewalk 88.4651 -
building 94.4346 -
wall 68.9881 -
fence 66.8948 -
pole 73.0672 -
traffic light 79.7022 -
traffic sign 83.302 -
vegetation 94.3555 -
terrain 74.3264 -
sky 96.0152 -
person 88.8138 73.8956
rider 76.3332 55.6746
car 96.6997 91.8083
truck 84.0098 51.3091
bus 94.3143 61.4593
train 91.7373 62.8559
motorcycle 74.7316 54.735
bicycle 79.3287 67.8052

 

Category results

Category IoU iIoU
flat 98.8362 -
nature 94.0587 -
object 78.5405 -
sky 96.0152 -
construction 94.5743 -
human 88.8131 74.6159
vehicle 96.2725 90.1614

 

Links

Download results as .csv file

Benchmark page