Method Details

Details for method 'FSFNet'


Method overview

name FSFNet
challenge pixel-level semantic labeling
details Semantic segmentation is performed to understand an image at the pixel level; it is widely used in the field of autonomous driving. In recent years, deep neural networks achieve good accuracy performance; however, there exist few models that have a good trade-off between high accuracy and low inference time. In this paper, we propose a fast spatial feature network (FSFNet), an optimized lightweight semantic segmentation model using an accelerator, offering high performance as well as faster inference speed than current methods. FSFNet employs the FSF and MRA modules. The FSF module has three different types of subset modules to extract spatial features efficiently. They are designed in consideration of the size of the spatial domain. The multi-resolution aggregation module combines features that are extracted at different resolutions to reconstruct the segmentation image accurately. Our approach is able to run at over 203 FPS at full resolution 1024 x 2048) in a single NVIDIA 1080Ti GPU, and obtains a result of 69.13% mIoU on the Cityscapes test dataset. Compared with existing models in real-time semantic segmentation, our proposed model retains remarkable accuracy while having high FPS that is over 30% faster than the state-of-the-art model. The experimental results proved that our model is an ideal approach for the Cityscapes dataset.
publication Accelerator-Aware Fast Spatial Feature Network for Real-Time Semantic Segmentation
Minjong Kim, Byungjae Park, Suyoung Chi
IEEE Access
project page / code
used Cityscapes data fine annotations
used external data ImageNet
runtime 0.0049261 s
1080Ti, TensorRT v5.1.5
subsampling no
submission date May, 2020
previous submissions


Average results

Metric Value
IoU Classes 69.1319
iIoU Classes 43.0262
IoU Categories 86.5888
iIoU Categories 72.554


Class results

Class IoU iIoU
road 97.7055 -
sidewalk 81.1635 -
building 90.2109 -
wall 41.7583 -
fence 47.0695 -
pole 54.1891 -
traffic light 61.1365 -
traffic sign 65.3923 -
vegetation 91.8746 -
terrain 69.4297 -
sky 94.2097 -
person 77.8652 58.9941
rider 57.8774 34.4389
car 92.887 86.6849
truck 47.3863 22.3812
bus 64.4488 33.7451
train 59.4483 29.0003
motorcycle 53.1812 27.8296
bicycle 66.2731 51.1351


Category results

Category IoU iIoU
flat 98.2026 -
nature 91.5635 -
object 61.2245 -
sky 94.2097 -
construction 90.4474 -
human 78.5092 60.3739
vehicle 91.9643 84.7342



Download results as .csv file

Benchmark page