Multi-task learning is effective for object detection and segmentation, which are closely related to each other and necessary for automated driving. However, there is a problem with the learning process in conventional multi-task learning models. In multi-task learning, common features among downstream tasks are first extracted by a backbone network. Then, these features are used for different downstream tasks. Since the required feature is different depending on the downstream task, it is necessary to extract features suitable for each downstream task. In this paper, we propose a multi-tasking model that introduces BiFPN feature fusion method for automated driving tasks and the Next-ViT model utilizing CNN and Transformer to extract features. From the evaluation experiments of automated driving tasks, we confirmed that the proposed method improves the accuracy of multi-task learning.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    High-Precision for Multi-Task Learning from In-Vehicle Camera using BiFPN


    Contributors:


    Publication date :

    2024-06-02


    Size :

    3368439 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    TF-BiFPN Improves YOLOv5: Enhancing Small-Scale Multiclass Drone Detection in Dark

    Misbah, Maham / Orakazi, Farooq Alam / Tanveer, Laiba et al. | IEEE | 2025


    Multi Camera Vehicle Tracking Using OpenCV & Deep Learning

    Patil, Aishwarya / Jadhav, Sushant / Tigadi, Arun et al. | IEEE | 2023


    Vehicle Attribute Recognition Algorithm Based on Multi-task Learning

    Sun, Jingying / Jia, Chengzhe / Shi, Zhiguo | IEEE | 2019


    Precision of FLEET Velocimetry using High-Speed CMOS Camera Systems

    Peters, Christopher J. / Danehy, Paul M. / Bathel, Brett F. et al. | British Library Conference Proceedings | 2015


    Precision of FLEET Velocimetry using High-Speed CMOS Camera Systems

    Peters, Christopher J. / Danehy, Paul M. / Bathel, Brett F. et al. | AIAA | 2015