Intelligent vehicles clearly benefit from the expanded Field of View (FoV) of the 360° sensors, but the vast majority of available semantic segmentation training images are captured with pinhole cameras. In this work, we look at this problem through the lens of domain adaptation and bring panoramic semantic segmentation to a setting, where labelled training data originates from a different distribution of conventional pinhole camera images. First, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation, where a network trained on labelled examples from the source domain of pinhole camera data is deployed in a different target domain of panoramic images, for which no labels are available. To validate this idea, we collect and publicly release Densepass - a novel densely annotated dataset for panoramic segmentation under cross-domain conditions, specifically built to study the Pinhole→panoramictransfer and accompanied with pinhole camera training examples obtained from Cityscapes. Densepass covers both, labelled- and unlabelled 360° images, with the labelled data comprising 19 classes which explicitly fit the categories available in the source domain (i.e. pinhole) data. To meet the challenge of domain shift, we leverage the current progress of attention-based mechanisms and build a generic framework for cross-domain panoramic semantic segmentation based on different variants of attention-augmented domain adaptation modules. Our framework facilitates information exchange at local- and global levels when learning the domain correspondences and improves the domain adaptation performance of two standard segmentation networks by 6.05% and 11.26% in Mean IoU.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange


    Contributors:


    Publication date :

    2021-09-19


    Size :

    1766887 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Unsupervised Domain Adaptation via Shared Content Representation for Semantic Segmentation

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


    Threshold-Adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation

    Yan, Weihao / Qian, Yeqiang / Wang, Chunxiang et al. | IEEE | 2023


    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


    PASS: Panoramic Annular Semantic Segmentation

    Yang, Kailun / Hu, Xinxin / Bergasa, Luis M. et al. | IEEE | 2020