MFNet: Multi-Feature Fusion Network for Real-Time Semantic Segmentation in Road Scenes

Nov 1, 2022·
Mengxu Lu
,
Zhenxue Chen
,
Chengyun Liu
,
Sile Ma
,
Lei Cai
Hao Qin
Hao Qin
· 1 min read
Abstract
MFNet is a real-time semantic segmentation network for road scenes. It combines attention, semantic, and spatial-information branches with asymmetric factorized blocks to balance accuracy, speed, and parameter efficiency.
Type
Publication
IEEE Transactions on Intelligent Transportation Systems
publications

MFNet is designed for practical real-time semantic segmentation, reaching strong accuracy-speed tradeoffs on road-scene benchmarks.

Semantic Segmentation Intelligent Transportation Efficient Networks
Hao Qin
Authors
Hao Qin
Ph.D. Student in Artificial Intelligence
I am a Ph.D. student in the College of Computer Science and Technology at Zhejiang University. My research focuses on 3D vision, 3D Gaussian Splatting, 3D-AIGC, and multi-agent systems, with broader interests in self-supervised representation learning and embodied visual content creation.