With the rapid development of convolutional neural networks (CNNs), significant progress has been achieved in semantic segmentation. Despite the great success, such deep learning approaches require large scale real-world datasets with pixel-level annotations. However, considering that pixel-level labeling of semantics is extremely laborious, many researchers turn to utilize synthetic data with free annotations. But due to the clear domain gap, the segmentation model trained with the synthetic images tends to perform poorly on the real-world datasets. Unsupervised domain adaptation (UDA) for semantic segmentation recently gains an increasing research attention, which aims at alleviating the domain discrepancy. Existing methods in this scope either simply align features or the outputs across the source and target domains or have to deal with the complex image processing and post-processing problems. In this work, we propose a novel multi-level UDA model named Confidence-and-Refinement Adaptation Model (CRAM), which contains a confidence-aware entropy alignment (CEA) module and a style feature alignment (SFA) module. Through CEA, the adaptation is done locally via adversarial learning in the output space, making the segmentation model pay attention to the high-confident predictions. Furthermore, to enhance the model transfer in the shallow feature space, the SFA module is applied to minimize the appearance gap across domains. Experiments on two challenging UDA benchmarks “GTA5-to-Cityscapes” and “SYNTHIA-to-Cityscapes” demonstrate the effectiveness of CRAM. We achieve comparable performance with the existing state-of-the-art works with advantages in simplicity and convergence speed.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation


    Beteiligte:
    Zhang, Xiaohong (Autor:in) / Chen, Yi (Autor:in) / Shen, Ziyi (Autor:in) / Shen, Yuming (Autor:in) / Zhang, Haofeng (Autor:in) / Zhang, Yudong (Autor:in)


    Erscheinungsdatum :

    2022-07-01


    Format / Umfang :

    5460742 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    CONFIDENCE-ESTIMATED DOMAIN ADAPTATION

    ROSMAN GUY | Europäisches Patentamt | 2021

    Freier Zugriff

    Situation-Aware Model Refinement for Semantic Image Segmentation

    Habermayr, Lukas / Hofbauer, Markus / Zacchi, Joao-Vitor et al. | IEEE | 2021


    Unsupervised Domain Adaptation via Shared Content Representation for Semantic Segmentation

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



    Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation

    Niemeijer, Joshua / Schäfer, P. Jörg | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2021

    Freier Zugriff