Unsupervised domain adaptation has been used to reduce the domain shift, which would improve the performance of semantic segmentation on unlabeled real-world data. How-ever, existing methods do not cater to the specific characteristics of traffic scene elements, leading to suboptimal alignment outcomes. In this paper, we propose a novel domain adaptation method for semantic segmentation of road scenes via unsu-pervised alignment of traffic elements. Firstly, a self-training framework is developed, which distinguishes the differential features between dynamic and static traffic elements, providing more accurate alignment training. Then, we designed a dynamic and static traffic elements alignment module to achieve cross-domain feature matching between the source and the target domain images. The cosine similarity maximization is applied to the alignment of dynamic traffic elements, while the prototype learning is utilized for the static traffic elements. Furthermore, the element alignment loss functions for dynamic and static traffic elements are designed to optimize the alignment modules. The experimental results demonstrate that the proposed method is superior to the existing methods on G TAS→Cityscapes task, which is applicable to semantic segmentation of road scenes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Unsupervised Alignment of Traffic Elements for Domain Adaptive Semantic Segmentation


    Beteiligte:
    Gao, Yuan (Autor:in) / Li, Yaochen (Autor:in) / Zhang, Tengwen (Autor:in) / Qiu, Chao (Autor:in) / Liu, Yuehu (Autor:in)


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    1872518 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Threshold-Adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation

    Yan, Weihao / Qian, Yeqiang / Wang, Chunxiang et al. | IEEE | 2023



    Domain-Incremental Semantic Segmentation for Traffic Scenes

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


    Unsupervised Domain Adaptation via Shared Content Representation for Semantic Segmentation

    Hubschneider, Christian / Birkenbach, Marius / Zollner, J. Marius | IEEE | 2021


    Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

    Termohlen, Jan-Aike / Klingner, Marvin / Brettin, Leon J. et al. | IEEE | 2021