Method Details


Details for method 'SwiftNetRN-18 ensemble'

 

Method overview

name SwiftNetRN-18 ensemble
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 February, 2019
previous submissions

 

Average results

Metric Value
IoU Classes 76.4547
iIoU Classes 51.4179
IoU Categories 90.0754
iIoU Categories 76.495

 

Class results

Class IoU iIoU
road 98.5232 -
sidewalk 85.3919 -
building 92.507 -
wall 49.1117 -
fence 53.8861 -
pole 64.1871 -
traffic light 71.1276 -
traffic sign 76.3169 -
vegetation 93.0896 -
terrain 71.0368 -
sky 95.545 -
person 84.7798 64.96
rider 67.4689 43.5078
car 95.6487 89.0753
truck 67.5222 32.4976
bus 80.4864 44.0287
train 68.2976 41.214
motorcycle 63.4647 37.7642
bicycle 74.2478 58.2952

 

Category results

Category IoU iIoU
flat 98.6471 -
nature 92.777 -
object 70.6333 -
sky 95.545 -
construction 92.771 -
human 85.1863 66.4017
vehicle 94.9685 86.5883

 

Links

Download results as .csv file

Benchmark page