We propose a convolutional network with hierarchical classifiers for per-pixel semantic segmentation, which is able to be trained on multiple, heterogeneous datasets and exploit their semantic hierarchy. Our network is the first to be simultaneously trained on three different datasets from the intelligent vehicles domain, i.e. Cityscapes, GTSDB and Mapillary Vistas, and is able to handle different semantic levelof-detail, class imbalances, and different annotation types, i.e. dense per-pixel and sparse bounding-box labels. We assess our hierarchical approach, by comparing against flat, nonhierarchical classifiers and we show improvements in mean pixel accuracy of 13.0% for Cityscapes classes and 2.4% for Vistas classes and 32.3% for GTSDB classes. Our implementation achieves inference rates of 17 fps at a resolution of 520 x 706 for 108 classes running on a GPU.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation


    Contributors:


    Publication date :

    2018-06-01


    Size :

    3719414 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On Boosting Semantic Street Scene Segmentation with Weak Supervision

    Meletis, Panagiotis / Dubbelman, Gijs | IEEE | 2019



    Semantic Segmentation for Traffic Scene Understanding Based on Mobile Networks

    Bai, Jie / Huang, Libo / Hao, Peihan et al. | SAE Technical Papers | 2018


    Semantic Segmentation for Traffic Scene Understanding Based on Mobile Networks

    Hao, Peihan / Chen, Sihan / Bai, Jie et al. | British Library Conference Proceedings | 2018


    Semantic video scene segmentation and transfer

    Gritti, T. / Damkat, C. / Monaci, G. | British Library Online Contents | 2014