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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:


    Publication date :

    2023-06-04


    Size :

    2373885 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Adversarial Semi-supervised Multi-domain Tracking

    Meshgi, Kourosh / Mirzaei, Maryam Sadat | British Library Conference Proceedings | 2021



    Improving GAN-based Domain Adaptation for Object Detection

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


    Unreliability-Aware Disentangling for Cross-Domain Semi-supervised Pedestrian Detection

    Wu, Wenhao / Wu, Si / Wong, Hau-San | British Library Conference Proceedings | 2023


    Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation

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