Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains. While UDA methods have access to unlabeled target images, domain generalization does not involve any target data and only learns generalized features from a source domain. Image-style randomization or augmentation is a popular approach to improve network generalization without access to the target domain. Complex methods are often proposed that disregard the potential of simple image augmentations for out-of-domain generalization. For this reason, we systematically study the in- and out-of-domain generalization capabilities of simple, rule-based image augmentations like blur, noise, color jitter and many more. Based on a full factorial design of experiment design we provide a systematic statistical evaluation of augmentations and their interactions. Our analysis provides both, expected and unexpected, outcomes. Expected, because our experiments confirm the common scientific standard that combination of multiple different augmentations outperforms single augmentations. Unexpected, because combined augmentations perform competitive to state-of-the-art domain generalization approaches, while being significantly simpler and without training overhead. On the challenging synthetic-to-real domain shift between Synthia and Cityscapes we reach 39.5% mIoU compared to 40.9% mIoU of the best previous work. When additionally employing the recent vision transformer architecture DAFormer we outperform these benchmarks with a performance of 44.2% mIoU.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Augmentation-based Domain Generalization for Semantic Segmentation


    Beteiligte:


    Erscheinungsdatum :

    2023-06-04


    Format / Umfang :

    901407 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    ImDeeplabV3plus with instance selective whitening loss in domain generalization semantic segmentation

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

    Freier Zugriff

    ImDeeplabV3plus with instance selective whitening loss in domain generalization semantic segmentation

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

    Freier Zugriff


    Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation

    Qiu, Shoumeng / Chen, Jie / Lai, Chenghang et al. | IEEE | 2024

    Freier Zugriff

    Multi-Domain Semantic-Segmentation using Multi-Head Model

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