Recently, boundary information has gained great attraction for semantic segmentation. This paper presents a novel encoder-decoder network, called BANet, for accurate semantic segmentation, where boundary information is employed as an additional assistance for producing more consistent segmentation outputs. BANet is composed of three components: the pre-trained backbone using dilated-ResNet101, semantic flow branch (SFB) and boundary flow branch (BFB) for semantic segmentation and boundary detection, respectively. More specifically, to delineate more accurate object shapes and boundaries, a global attention block (GAB) is designed in SFB as global guidance for high-level feature. On the other hand, BFB directly extracts features on boundaries, avoiding the unexpected interference from the non-boundary parts. Finally, we adopt a joint loss function to further optimize the segmentation results and boundary outputs synchronously. Moreover, compared with previous state-of-the-art methods, e.g., non-local block and ASPP module, our BFB leverages detection accuracy and computational efficiency in a lightweight fashion. To evaluate BANet, we have conducted extensive experiments on several semantic segmentation datasets: Cityscapes, PASCAL Context, and ADE20K. The experimental results show that, with the aid of boundary information, BANet is able to produce more consistent segmentation predictions with accurately delineated object shapes and boundaries, leading to the state-of-the-art performance on Cityscapes, and competitive results on PASCAL Context and ADE20K with respect to recent semantic segmentation networks.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Beteiligte:
    Zhou, Quan (Autor:in) / Qiang, Yong (Autor:in) / Mo, Yuwei (Autor:in) / Wu, Xiaofu (Autor:in) / Latecki, Longin Jan (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.12.2022


    Format / Umfang :

    4306300 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    CCSDS Decoder/Encoder Boards

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


    UNSUPERVISED ENCODER-DECODER NEURAL NETWORK SECURITY EVENT DETECTION

    KORAL YARON / ZHANG RENSHENG WANG / NOEL ERIC et al. | Europäisches Patentamt | 2020

    Freier Zugriff

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

    Tang, Quan / Liu, Fagui / Zhang, Tong et al. | IEEE | 2022


    Unsupervised encoder-decoder neural network security event detection

    KORAL YARON / ZHANG RENSHENG WANG / NOEL ERIC et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    UNSUPERVISED ENCODER-DECODER NEURAL NETWORK SECURITY EVENT DETECTION

    KORAL YARON / ZHANG RENSHENG WANG / NOEL ERIC et al. | Europäisches Patentamt | 2023

    Freier Zugriff