Method Details

Details for method 'Fast-SCNN (Quarter-resolution)'


Method overview

name Fast-SCNN (Quarter-resolution)
challenge pixel-level semantic labeling
details The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional neural network (Fast-SCNN), an above real-time semantic segmentation model on high resolution image data (1024x2048px) suited to efficient computation on embedded devices with low memory. Building on existing two-branch methods for fast segmentation, we introduce our `learning to downsample' module which computes low-level features for multiple resolution branches simultaneously. Our network combines spatial detail at high resolution with deep features extracted at lower resolution, yielding an accuracy of 68.0% mean intersection over union at 123.5 frames per second on Cityscapes. We also show that large scale pre-training is unnecessary. We thoroughly validate our metric in experiments with ImageNet pre-training and the coarse labeled data of Cityscapes. Finally, we show even faster computation with competitive results on subsampled inputs, without any network modifications.
publication Fast-SCNN: Fast Semantic Segmentation Network
Rudra P K Poudel, Stephan Liwicki, Roberto Cipolla
project page / code
used Cityscapes data fine annotations
used external data
runtime 0.00206 s
Nvidia Titan Xp (Pascal)
subsampling 4
submission date November, 2018
previous submissions


Average results

Metric Value
IoU Classes 51.9292
iIoU Classes 23.0119
IoU Categories 74.1649
iIoU Categories 48.2369


Class results

Class IoU iIoU
road 96.3406 -
sidewalk 70.4595 -
building 83.1103 -
wall 26.0995 -
fence 23.5008 -
pole 18.6551 -
traffic light 26.1479 -
traffic sign 33.1417 -
vegetation 84.504 -
terrain 55.7191 -
sky 89.5119 -
person 55.1668 28.1508
rider 35.4404 10.2066
car 86.8067 70.7005
truck 38.7097 10.3824
bus 47.386 18.0632
train 46.683 18.1863
motorcycle 27.2933 6.94711
bicycle 41.9791 21.4585


Category results

Category IoU iIoU
flat 96.7545 -
nature 83.8904 -
object 25.4159 -
sky 89.5119 -
construction 82.8695 -
human 55.6375 28.7441
vehicle 85.0747 67.7297



Download results as .csv file

Benchmark page