Existing domain generalization semantic segmentation (DGSS) methods have achieved remarkable performance on unseen domains by generating stylized images to increase the diversity of training data. However, since the training data is usually class-imbalanced, uniform style randomization is unable to generate diverse minority classes. This means that models may overfit to the minority classes, resulting in suboptimal performance on the minority classes. In addition, the image-level style randomization may also corrupt the class-discriminative regions of objects, leading to a loss of the class-discriminative representation. To address these issues, a novel class-balanced sampling and discriminative stylization (CSDS) approach is proposed for DGSS. Specifically, first, a pixel-level class-balanced sampling (PCS) strategy is proposed to adaptively sample patches of the minority classes from the source domain images and paste the sampled patches on the input images. Unlike existing class sampling strategies that fix the minority classes, the PCS strategy dynamically determines the minority classes by estimating the class distribution after each sampling. Then, a class-discriminative style randomization (CSR) strategy is proposed to increase the style diversity of the sampled patches while preserving the class-discriminative regions. Finally, since the pasting positions of the sampled patches are uncertain, which may confuse the semantic relations between the classes, a semantic consistency constraint is proposed to ensure the learning of reliable semantic relations. Extensive experiments demonstrate that the proposed approach achieves superior performance compared to existing DGSS methods on multiple benchmarks. The source code has been released on https://github.com/seabearlmx/CSDS.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Class-Balanced Sampling and Discriminative Stylization for Domain Generalization Semantic Segmentation


    Contributors:
    Liao, Muxin (author) / Tian, Shishun (author) / Wei, Binbin (author) / Zhang, Yuhang (author) / Zou, Wenbin (author) / Li, Xia (author)


    Publication date :

    2025-02-01


    Size :

    4796807 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Augmentation-based Domain Generalization for Semantic Segmentation

    Schwonberg, Manuel / Bouazati, Fadoua El / Schmidt, Nico M. et al. | IEEE | 2023


    Image-Based Stereoscopic Stylization

    Stavrakis, E. / Bleyer, M. / Markovic, D. et al. | British Library Conference Proceedings | 2005


    ImDeeplabV3plus with instance selective whitening loss in domain generalization semantic segmentation

    Zhang, You / Chen, Houjin / Li, Yanfeng et al. | Wiley | 2023

    Free access

    ImDeeplabV3plus with instance selective whitening loss in domain generalization semantic segmentation

    You Zhang / Houjin Chen / Yanfeng Li et al. | DOAJ | 2023

    Free access

    BEHAVIOR-CONDITIONED MESSAGE STYLIZATION

    ROSMAN GUY / DOS REIS COSTA JEAN MARCEL / YASUDA HIROSHI et al. | European Patent Office | 2025

    Free access