In recent years, the surge of artificial intelligence has propelled autonomous driving technology to the forefront, capturing growing interest and enthusiasm. As a sub-module within autonomous driving, research in traffic sign detection and recognition has significantly advanced with a growing focus on utilizing deep learning methods. Nevertheless, in complex real-world road scenarios, traffic signs often exhibit a long-tailed distribution, with the majority of instances concentrated in a few frequent categories and a scarcity in the remaining ones. Considering conventional Traffic Sign Detection and Recognition methods are crafted using manually curated datasets, the class imbalance may detrimentally impact the efficacy of the detection model. In this paper, we first propose a gradient-guided loss reweighting model that dynamically reweights the loss for positive and negative samples based on the cumulative gradients across each category. Additionally, a classification bias-based refinement module is proposed to fine-tune these weights during training, based on the false positive and false negative rate. This serves to suppress a drop in precision for tail categories resulting from the gradient-guided loss reweighting module, thus further balancing the entire training process for improved results. Extensive experiments are performed on the TT100K and GTSDB datasets, yielding significant advancements surpassing state-of-the-art methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A More Balanced Loss-Reweighting Method for Long-Tailed Traffic Sign Detection and Recognition


    Contributors:
    Wang, Yinjie (author) / Huang, Weiguo (author) / Li, Jiajie (author) / Du, Guifu (author) / Wang, Xiang (author) / Wenjuan, E. (author) / Shi, Juanjuan (author)

    Published in:

    Publication date :

    2024-12-01


    Size :

    1792037 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Long-Tailed Traffic Sign Detection Using Attentive Fusion and Hierarchical Group Softmax

    Gao, Erfeng / Huang, Weiguo / Shi, Juanjuan et al. | IEEE | 2022


    TRAFFIC SIGN RECOGNITION DEVICE AND TRAFFIC SIGN RECOGNITION METHOD

    MIYASATO KAZUHIRO / KOYASU TOSHIYA | European Patent Office | 2023

    Free access

    TRAFFIC SIGN RECOGNITION DEVICE AND TRAFFIC SIGN RECOGNITION METHOD

    SHINOMIYA TERUHIKO | European Patent Office | 2017

    Free access

    Traffic Sign Detection and Recognition

    Pillai, Preeti S. / Kinnal, Bhagyashree / Pattanashetty, Vishal et al. | Springer Verlag | 2022


    Traffic Sign Detection and Recognition

    Habibi Aghdam, Hamed / Jahani Heravi, Elnaz | Springer Verlag | 2017