Existing RGB-T semantic segmentation networks adopt the one-way RGB-T data fusion strategy that enhances RGB features with thermal features, resulting in the underutilization of thermal information. To address it, we propose a novel RGB-T fusion network termed MMNet which introduces an adaptively mutual enhancement mechanism to enhance RGB and thermal features by each other in the encoder, as well as hierarchically aggregates multi-resolution RGB-T features in the decoder. Experimental results show that MMNet achieves state-of-the-art 56.8% mIoU, being 1.66×  faster than the best previous work.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MMNet: RGB-t Semantic Segmentation Network Based on Multi-scale and Adaptively Mutual Enhancement Mechanism


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Wu, Meiping (editor) / Niu, Yifeng (editor) / Gu, Mancang (editor) / Cheng, Jin (editor) / Wang, Chao (author) / Wu, Tao (author)

    Conference:

    International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021



    Publication date :

    2022-03-18


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Shape-Based Mutual Segmentation

    Riklin-Raviv, T. / Sochen, N. / Kiryati, N. | British Library Online Contents | 2008


    When Visual Disparity Generation Meets Semantic Segmentation: A Mutual Encouragement Approach

    Zhang, Xiaohong / Chen, Yi / Zhang, Haofeng et al. | IEEE | 2021