Method Details

Details for method 'CABiNet'


Method overview

name CABiNet
challenge pixel-level semantic labeling
details With the increasing demand of autonomous machines, pixel-wise semantic segmentation for visual scene understanding needs to be not only accurate but also efficient for any potential real-time applications. In this paper, we propose CABiNet (Context Aggregated Bi-lateral Network), a dual branch convolutional neural network (CNN), with significantly lower computational costs as compared to the state-of-the-art, while maintaining a competitive prediction accuracy. Building upon the existing multi-branch architectures for high-speed semantic segmentation, we design a cheap high resolution branch for effective spatial detailing and a context branch with light-weight versions of global aggregation and local distribution blocks, potent to capture both long-range and local contextual dependencies required for accurate semantic segmentation, with low computational overheads. Specifically, we achieve 76.6% and 75.9% mIOU on Cityscapes validation and test sets respectively, at 76 FPS on an NVIDIA RTX 2080Ti and 8 FPS on a Jetson Xavier NX. Codes and training models will be made publicly available.
publication CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation
Saumya Kumaar, Ye Lyu, Francesco Nex, Michael Ying Yang
project page / code
used Cityscapes data fine annotations
used external data
runtime 0.013 s
subsampling no
submission date January, 2021
previous submissions


Average results

Metric Value
IoU Classes 75.9588
iIoU Classes 48.9827
IoU Categories 91.0554
iIoU Categories 75.7435


Class results

Class IoU iIoU
road 98.1861 -
sidewalk 83.1818 -
building 92.9431 -
wall 44.1112 -
fence 62.0063 -
pole 71.0758 -
traffic light 78.3811 -
traffic sign 80.8305 -
vegetation 93.8981 -
terrain 70.9309 -
sky 95.6521 -
person 84.4958 61.334
rider 67.0964 41.6659
car 95.5884 90.9312
truck 59.9507 27.8904
bus 70.2586 38.3365
train 57.7441 32.7275
motorcycle 61.3951 34.7883
bicycle 75.4904 64.1876


Category results

Category IoU iIoU
flat 98.6042 -
nature 93.3344 -
object 76.5972 -
sky 95.6521 -
construction 93.4715 -
human 84.9766 62.767
vehicle 94.7517 88.72



Download results as .csv file

Benchmark page