Method Details


Details for method 'SAIT'

 

Method overview

name SAIT
challenge pixel-level semantic labeling
details Given Training Data Only No Post-Processing (like CRF) This method was previously listed as "GSTE".
publication Anonymous
project page / code
used Cityscapes data fine annotations, coarse annotations
used external data ImageNet
runtime 1 s
GPU TITAN X
subsampling no
submission date August, 2016
previous submissions 1, 2, 3, 4, 5, 6, 7

 

Average results

Metric Value
IoU Classes 75.8488
iIoU Classes 49.629
IoU Categories 88.9625
iIoU Categories 73.8927

 

Class results

Class IoU iIoU
road 98.4216 -
sidewalk 84.9827 -
building 92.1364 -
wall 51.8225 -
fence 55.254 -
pole 60.2025 -
traffic light 68.085 -
traffic sign 74.0192 -
vegetation 92.9779 -
terrain 71.0009 -
sky 94.9978 -
person 82.3911 61.094
rider 64.7505 39.0238
car 95.0667 88.05
truck 67.9164 33.1841
bus 81.2205 44.5409
train 75.5708 43.204
motorcycle 59.2417 33.9226
bicycle 71.0697 54.0128

 

Category results

Category IoU iIoU
flat 98.5315 -
nature 92.6248 -
object 67.3656 -
sky 94.9978 -
construction 92.4728 -
human 82.5056 62.0522
vehicle 94.2396 85.7332

 

Links

Download results as .csv file

Benchmark page