Image context in image is crucial for improving scene labeling. While the existing methods only exploit local context generated from a small surrounding area of an image patch or a pixel, the long-range and global contextual information is often ignored. To handle this issue, we propose a novel approach for scene labeling by multi-level contextual recurrent neural networks (RNNs). We encode three kinds of contextual cues, viz., local context, global context, and image topic context in structural RNNs to model long-range local and global dependencies in an image. In this way, our method is able to “see” the image in terms of both long-range local and holistic views, and make a more reliable inference for image labeling. Besides, we integrate the proposed contextual RNNs into hierarchical convolutional neural networks, and exploit dependence relationships at multiple levels to provide rich spatial and semantic information. Moreover, we adopt an attention model to effectively merge multiple levels and show that it outperforms average- or max-pooling fusion strategies. Extensive experiments demonstrate that the proposed approach achieves improved results on the CamVid, KITTI, SiftFlow, Stanford Background, and Cityscapes data sets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-Level Contextual RNNs With Attention Model for Scene Labeling


    Contributors:
    Fan, Heng (author) / Mei, Xue (author) / Prokhorov, Danil (author) / Ling, Haibin (author)


    Publication date :

    2018-11-01


    Size :

    2649135 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Semantic Scene Labeling via Deep Nested Level Set

    Zhang, Pingping / Liu, Wei / Lei, Yinjie et al. | IEEE | 2021


    METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS

    WANG ZIRAN / HAN KYUNGTAE / GUPTA ROHIT | European Patent Office | 2024

    Free access

    Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs

    Engel, Nico / Hoermann, Stefan / Henzler, Philipp et al. | IEEE | 2018


    GapFormer: Fast Autoregressive Transformers meet RNNs for Personalized Adaptive Cruise Control

    Sachdeva, Noveen / Wang, Ziran / Han, Kyungtae et al. | IEEE | 2022


    Labeling Complete Surfaces in Scene Understanding

    Guo, R. / Hoiem, D. | British Library Online Contents | 2015