While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation using a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset. Our approach is also very efficient, allowing us to perform inference at more then 23 frames per second. Training scripts and trained weights to reproduce our results can be found here: https://github.com/MarvinTeichmann/MultiNet


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving


    Beteiligte:
    Teichmann, Marvin (Autor:in) / Weber, Michael (Autor:in) / Zollner, Marius (Autor:in) / Cipolla, Roberto (Autor:in) / Urtasun, Raquel (Autor:in)


    Erscheinungsdatum :

    01.06.2018


    Format / Umfang :

    5553842 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    MULTINET: REAL-TIME JOINT SEMANTIC REASONING FOR AUTONOMOUS DRIVING

    Teichmann, Marvin / Weber, Michael / Zöllner, Marius et al. | British Library Conference Proceedings | 2018


    Real-Time Monocular Joint Perception Network for Autonomous Driving

    Li, Keqiang / Xiong, Hui / Liu, Jinxin et al. | IEEE | 2022



    A real-time semantic segmentation method for autonomous driving in surface mine

    Wei, Qinggong / Song, Ruiqi / Yang, Xue et al. | IEEE | 2022


    MLRFNet: Multi-Level Real-Time Fusion Semantic Segmentation Network for Autonomous Driving

    Ma, Xiaochuan / Xun, Zhijie / Mao, Bomin et al. | IEEE | 2025