FRNet: Factorized and Regular Blocks Network for Semantic Segmentation in Road Scene

Nowadays, semantic segmentation methods for systems in road scene have a great demand. Most existing methods focus on high accuracy with low inference speed. And some approaches emphasize on speed, significantly sacrificing model accuracy. To make a trade-off between accuracy and inference speed, we propose a real-time network for semantic segmentation titled Factorized and Regular Network (FRNet), which employs an asymmetric encoder-decoder architecture with Factorized and Regular (FR) blocks. Our method achieves 70.4% mIoU on the Cityscapes test set with 1 million parameters at a speed of 127 frames per second (FPS) on a single Titan Xp at a resolution of 512 x 1024. We evaluate FRNet on Cityscapes, Camvid, Kitti, and Gatech datasets to identify that our network stands out from other state-of-the-art networks.

Automated summary

This paper proposes a real-time network for semantic segmentation called FRNet, which achieves a trade-off between accuracy and inference speed by employing Factorized and Regular (FR) blocks and an asymmetric encoder-decoder architecture. Experimental results on multiple datasets demonstrate that our network outperforms other state-of-the-art networks.