Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning based methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can provide accurate annotations. However, the performance of the semantic segmentation model trained with synthetic datasets will significantly degenerate in the actual scenes. Unsupervised domain adaptation (UDA) for semantic segmentation is used to reduce the domain gap and improve the performance on the target domain. Existing adversarial-based and self-training methods usually involve complex training procedures, while entropy-based methods have recently received attention for their simplicity and effectiveness. However, entropy-based UDA methods have problems that they barely optimize hard samples and lack an explicit semantic connection between the source and target domains. In this paper, we propose a novel two-stage entropy-based UDA method for semantic segmentation. In stage one, we design a threshold-adaptative unsupervised focal loss to regularize the prediction in the target domain. It first introduces unsupervised focal loss into UDA for semantic segmentation, helping to optimize hard samples and avoiding generating unreliable pseudo-labels in the target domain. In stage two, we employ cross-domain image mixing (CIM) to bridge the semantic knowledge between two domains and incorporate long-tail class pasting to alleviate the class imbalance problem. Extensive experiments on synthetic-to-real and cross-city benchmarks demonstrate the effectiveness of our method. It achieves state-of-the-art performance using DeepLabV2, as well as competitive performance using the lightweight BiSeNet with great advantages in training and inference time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Yan, Weihao (author) / Qian, Yeqiang (author) / Wang, Chunxiang (author) / Yang, Ming (author)


    Publication date :

    2023-01-01


    Size :

    4731418 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    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