Real-time semantic segmentation is in intense demand for the application of autonomous driving. Most of the semantic segmentation models tend to use large feature maps and complex structures to enhance the representation power for high accuracy. However, these inefficient designs increase the amount of computational costs, which hinders the model to be applied on autonomous driving. In this paper, we propose a lightweight real-time segmentation model, named Parallel Complement Network (PCNet), to address the challenging task with fewer parameters. A Parallel Complement layer is introduced to generate complementary features with a large receptive field. It provides the ability to overcome the problem of similar feature encoding among different classes, and further produces discriminative representations. With the inverted residual structure, we design a Parallel Complement block to construct the proposed PCNet. Extensive experiments are carried out on challenging road scene datasets, i.e., CityScapes and CamVid, to make comparison against several state-of-the-art real-time segmentation models. The results show that our model has promising performance. Specifically, PCNet* achieves 72.9% Mean IoU on CityScapes using only 1.5M parameters and reaches 79.1 FPS with $1024\times 2048$ resolution images on GTX 2080Ti. Moreover, our proposed system achieves the best accuracy when being trained from scratch.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Beteiligte:
    Lv, Qingxuan (Autor:in) / Sun, Xin (Autor:in) / Chen, Changrui (Autor:in) / Dong, Junyu (Autor:in) / Zhou, Huiyu (Autor:in)


    Erscheinungsdatum :

    01.05.2022


    Format / Umfang :

    2510378 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



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

    Lu, Mengxu / Chen, Zhenxue / Liu, Chengyun et al. | IEEE | 2022




    Multi Path Real-time Semantic Segmentation Network in Road Scenarios

    Pengfei, Gao / Xiaolong, Tian / Cuihong, Liu et al. | Springer Verlag | 2025


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

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