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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Augmentation-based Domain Generalization for Semantic Segmentation


    Contributors:


    Publication date :

    2023-06-04


    Size :

    901407 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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


    Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation

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

    Free access

    Multi-Domain Semantic-Segmentation using Multi-Head Model

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