Semantic segmentation plays a critical role in scene understanding for self-driving vehicles. A line of efforts has proven that global context matters in urban scene segmentation due to massive scale changes. However, we find that existing methods suffer from local ambiguities when dissipating continuous local context, i.e. scrambling to a huge receptive field of global cues by coarse pooling. To this end, this paper proposes a new Context Aggregation Module (CAM) that consists of two primary components: context encoding using no coarse pooling but encoder-decoders with appropriate sampling scales and gated fusion that extends gate attention mechanism to balance different-scale context during feature fusion. Weeding out coarse pooling and applying the encoder-decoder inherits the merits of exploring global context while avoiding the drawback of losing local contextual continuity. We then construct a Context Aggregation Network (CANet) and conduct extensive evaluations on challenging autonomous driving benchmarks of Cityscapes, CamVid and BDD100K. Consistently improved results evidence the effectiveness. Notably, we attain competitive mIoU 82.7% on Cityscapes and optimal mIoU 80.5% on CamVid.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Compensating for Local Ambiguity With Encoder-Decoder in Urban Scene Segmentation


    Contributors:
    Tang, Quan (author) / Liu, Fagui (author) / Zhang, Tong (author) / Jiang, Jun (author) / Zhang, Yu (author) / Zhu, Boyuan (author) / Tang, Xuhao (author)

    Published in:

    Publication date :

    2022-10-01


    Size :

    4228320 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    BANet: Boundary-Assistant Encoder-Decoder Network for Semantic Segmentation

    Zhou, Quan / Qiang, Yong / Mo, Yuwei et al. | IEEE | 2022


    CCSDS Decoder/Encoder Boards

    Habinc, S. / Saunders, S. | Springer Verlag | 2022


    The CCSDS Decoder/Encoder Boards

    Habinc, Sandi | Springer Verlag | 2013



    ENCODER, DECODER, ENCODING METHOD, AND DECODING METHOD

    KANOH RYUICHI / ABE KIYOFUMI / NISHI TAKAHIRO et al. | European Patent Office | 2024

    Free access