This article introduces a versatile multi-task learning framework (UMT-Net) and an adaptive task weighting (ATW) training method, specifically designed for resource-constrained scenarios that demand parameter-efficient networks. The adaptable UMT-Net architecture includes a global-shared backbone based on an encoder, task-specific self-attention modules, inter-task joint-attention fusion modules, and feature-aggregating decoders. The ATW technique accounts for both short-term variation and long-term statistics of task losses, leading to a more stable training process. Extensive experiments on CityScapes and NYUv2 datasets reveal that UMT-Net outperforms baseline methods while requiring fewer computations, model parameters, and inference latency. In addition, we also conducted experiments on the autonomous driving dataset BDD100 K and achieved state-of-the-art performance. Furthermore, we deployed the model and carried out tests for generalization in real-world scenarios. Finally, our network architecture possesses the capability to be designed as a compact model with much fewer parameters, computational requirements, and inference time, while maintaining competitive performance, making it suitable for deployment on mobile devices.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    UMT-Net: A Uniform Multi-Task Network With Adaptive Task Weighting


    Beteiligte:
    Chen, Sihan (Autor:in) / Zheng, Lianqing (Autor:in) / Huang, Libo (Autor:in) / Bai, Jie (Autor:in) / Zhu, Xichan (Autor:in) / Ma, Zhixiong (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.01.2024


    Format / Umfang :

    25075697 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems

    Leang, Isabelle / Sistu, Ganesh / Burger, Fabian et al. | IEEE | 2020


    Multiple metric learning with query adaptive weights and multi-task re-weighting for person re-identification

    Jia, Jieru / Ruan, Qiuqi / An, Gaoyun et al. | British Library Online Contents | 2017


    An Adaptive Task Planning Method for UAVC Task Layer: DSTCA

    Ting Duan / Qun Li / Xin Zhou et al. | DOAJ | 2024

    Freier Zugriff

    MtpNet: Multi-Task Panoptic Driving Perception Network

    Li, Zheng / Yuan, Xiaohui / Sun, Bifan et al. | IEEE | 2025