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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Lv, Qingxuan (author) / Sun, Xin (author) / Chen, Changrui (author) / Dong, Junyu (author) / Zhou, Huiyu (author)


    Publication date :

    2022-05-01


    Size :

    2510378 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



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

    Lu, Mengxu / Chen, Zhenxue / Liu, Chengyun 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



    Attribute-aware Semantic Segmentation of Road Scenes for Understanding Pedestrian Orientations

    Sulistiyo, M. D. / Kawanishi, Y. / Deguchi, D. et al. | IEEE | 2018