FRNet: Factorized and Regular Blocks Network for Semantic Segmentation in Road Scene
Mengxu Lu, Zhenxue Chen, Q. M. Jonathan Wu, Nannan Wang, Xuewen Rong, Xinghe Yan
Abstract
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 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$512\times 1024$ </tex-math></inline-formula> . We evaluate FRNet on Cityscapes, Camvid, Kitti, and Gatech datasets to identify that our network stands out from other state-of-the-art networks.