This paper addresses the challenges in multi-target domain adaptive (MTDA) for semantic segmentation, aiming to learn a single model capable of adapting to multi-target domains. Existing methods solely focus on visual appearance (style) discrepancies, overlooking contextual variations across multi-target domains, resulting in limited performance. We propose a novel approach termed Masking-augmented Collaborative Domain Congregation (MacDC) to handle both style gap and contextual gap among multi-target domains. MacDC achieves this goal by generating image-level and region-level intermediate domains among multi-target domains. To further strengthen contextual alignment, MacDC applies multi-context masking that enforces the model’s understanding of diverse contexts. Notably, MacDC directly learns a single model for multi-target domain adaptation, significantly reducing training times and model parameters. Despite its simplicity, MacDC demonstrates superior performance compared to state-of-the-art MTDA segmentation methods on the syn-to-real and real-to-real benchmarks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MacDC: Masking-augmented Collaborative Domain Congregation for Multi-target Domain Adaptation in Semantic Segmentation


    Contributors:
    Pan, Fei (author) / He, Dong (author) / Yin, Xu (author) / Zhang, Chenshuang (author) / Kim, Munchurl (author)


    Publication date :

    2024-06-02


    Size :

    4727857 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    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


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

    Zhang, Xiaohong / Chen, Yi / Shen, Ziyi et al. | IEEE | 2022


    Unsupervised Domain Adaptation via Shared Content Representation for Semantic Segmentation

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


    Multi-Domain Semantic-Segmentation using Multi-Head Model

    Masaki, Shota / Hirakawa, Tsubasa / Yamashita, Takayoshi et al. | IEEE | 2021