In autonomous driving, millions of frames with various scenarios for training deep object detectors is required. Labeling such a large number of frames is a costly process, therefore additional data sources support the training task. However, domain gaps from different cameras, weather, or locations typically limit the performance.We apply semi-supervised object detection, which leverages labeled source and pseudo-labeled target domain data in an iterative training paradigm. In addition, we newly include state-of-the-art adversarial style transfer into the semi-supervised training by stylizing images from source and target domains. This reduces the domain gap and improves pseudo-label quality in cross-domain semi-supervised training.In experiments and ablation studies, we show that our novel training framework can improve state-of-the-art detection performance by up to +10.1% on standard domain adaptation benchmarks.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Improving Cross-Domain Semi-Supervised Object Detection with Adversarial Domain Adaptation


    Beteiligte:


    Erscheinungsdatum :

    04.06.2023


    Format / Umfang :

    2373885 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Improving GAN-based Domain Adaptation for Object Detection

    Menke, Maximilian / Wenzel, Thomas / Schwung, Andreas | IEEE | 2022



    Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation

    Hanselmann, Niklas / Schneider, Nick / Ortelt, Benedikt et al. | IEEE | 2021



    Domain Adaptation Grasp Network for Novel Object Grasp Detection

    Cai, Xiangting / Xu, Xin / Ren, Shuai et al. | Springer Verlag | 2022