Object instance segmentation in traffic scenes is an important research topic. For training instance segmentation models, synthetic data can potentially complement real data, alleviating manual effort on annotating real images. However, the data distribution discrepancy between synthetic data and real data hampers the wide applications of synthetic data. In light of that, we propose a virtual-real interaction method for object instance segmentation. This method works over synthetic images with accurate annotations and real images without any labels. The virtual-real interaction guides the model to learn useful information from synthetic data while keeping consistent with real data. We first analyze the data distribution discrepancy from a probabilistic perspective, and divide it into image-level and instance-level discrepancies. Then, we design two components to align these discrepancies, i.e., global-level alignment and local-level alignment. Furthermore, a consistency alignment component is proposed to encourage the consistency between the global-level and the local-level alignment components. We evaluate the proposed approach on the real Cityscapes dataset by adapting from virtual SYNTHIA, Virtual KITTI, and VIPER datasets. The experimental results demonstrate that it achieves significantly better performance than state-of-the-art methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes


    Beteiligte:
    Zhang, Hui (Autor:in) / Luo, Guiyang (Autor:in) / Tian, Yonglin (Autor:in) / Wang, Kunfeng (Autor:in) / He, Haibo (Autor:in) / Wang, Fei-Yue (Autor:in)


    Erscheinungsdatum :

    01.02.2021


    Format / Umfang :

    6033492 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Dynamic Segmentation of Traffic Scenes

    Giachetti, A. / Torre, V. / Cappello, M. et al. | British Library Conference Proceedings | 1995



    Domain-Incremental Semantic Segmentation for Traffic Scenes

    Liu, Yazhou / Chen, Haoqi / Lasang, Pongsak et al. | IEEE | 2025


    Understanding object relations in traffic scenes

    Hensel, Irina / Bachmann, Alexander / Hummel, Britta et al. | Tema Archiv | 2010