Although high-accuracy networks have been applied to semantic segmentation at present, their inference speeds remain slow. A trade-off between accuracy and speed is demanded for real-time applications. To approach this problem, we propose Multi-Feature Fusion Network (MFNet) with real-time efficient prediction capacity. MFNet adopts three branches (attention, semantic and spatial information) to capture low-level and high-level features. Additionally, MFNet exerts asymmetric factorized (AF) blocks to extract local and long-range features. As a result, without any pre-training or post-processing, MFNet using only 1.34 M parameters, achieves 72.1% mean intersection over union (mIoU) on the Cityscapes test set at a speed of 116 frames per second (FPS), with $512\times 1024$ high resolution on a single Titan Xp graphics card. Our network’s performance stands out from other state-of-the-art networks on four datasets (Cityscapes, CamVid, KITTI, and Gatech).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Lu, Mengxu (author) / Chen, Zhenxue (author) / Liu, Chengyun (author) / Ma, Sile (author) / Cai, Lei (author) / Qin, Hao (author)

    Published in:

    Publication date :

    2022-11-01


    Size :

    5114484 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Parallel Complement Network for Real-Time Semantic Segmentation of Road Scenes

    Lv, Qingxuan / Sun, Xin / Chen, Changrui et al. | IEEE | 2022



    Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

    Dong, Genshun / Yan, Yan / Shen, Chunhua et al. | IEEE | 2021