Recent progress of deep image classification models provides great potential for improving related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory limitations of contemporary GPUs. The extent of feature map caching required by convolutional backprop poses significant challenges even for moderately sized Pascal images, while requiring careful architectural considerations when input resolution is in the megapixel range. To address these concerns, we propose a novel ladder-style DenseNet-based architecture which features high modelling power, efficient upsampling, and inherent spatial efficiency which we unlock with checkpointing. The resulting models deliver high performance and allow training at megapixel resolution on commodity hardware. The presented experimental results outperform the state-of-the-art in terms of prediction accuracy and execution speed on Cityscapes, VOC 2012, CamVid and ROB 2018 datasets. Source code at https://github.com/ivankreso/LDN.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Efficient Ladder-Style DenseNets for Semantic Segmentation of Large Images


    Contributors:


    Publication date :

    2021-08-01


    Size :

    4364141 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Efficient Semantic Segmentation with Hyperspectral Images

    Peña, Fernando / Vidal Aguilar, Pilar / Suarez Gracia, Darío et al. | Springer Verlag | 2022


    POCKET STYLE FOLDING BOAT LADDER ASSEMBLY

    ROGERS ERIK / YOBE MICHAEL / STOCKMAN JOHN CB | European Patent Office | 2024

    Free access

    POCKET STYLE FOLDING BOAT LADDER ASSEMBLY

    ROGERS ERIK / YOBE MICHAEL / STOCKMAN JOHN CB | European Patent Office | 2024

    Free access

    Railroad semantic segmentation on high-resolution images

    Belyaev, Sergey / Popov, Igor / Shubnikov, Vladislav et al. | IEEE | 2020


    An Efficient Approach to Semantic Segmentation

    Csurka, G. / Perronnin, F. | British Library Online Contents | 2011