In this paper, we propose the first Test-Time Augmentation (TTA) method to estimate uncertainty and improve accuracy of pre-trained object detectors in the autonomous driving domain. We show, in an autonomous driving dataset, that even simple color-based augmentations are able to improve mean Average Precision (mAP) performance with respect to other state-of-the-art methods with the same purpose (Monte Carlo (MC) Dropout and Output Redundancy). Furthermore, we show that the quality of the estimated uncertainty and distributions can be improved, both in our method and in the state-of-the-art, if some of the parameters of the methods (bounding box selection and clustering criteria) are independently tuned for the classification and the localization subtasks of object detection.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Quantifying Object Detection Uncertainty in Autonomous Driving with Test-Time Augmentation


    Beteiligte:


    Erscheinungsdatum :

    04.06.2023


    Format / Umfang :

    1253154 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Evaluation of Point Cloud Data Augmentation for 3D-LiDAR Object Detection in Autonomous Driving

    Martins, Marta / Gomes, Iago P. / Wolf, Denis Fernando et al. | Springer Verlag | 2024



    Autonomous Driving Object Detection Platform

    Carabulea, Laurentiu / Pozna, Claudiu / Antonya, Csaba et al. | Springer Verlag | 2024


    Critical Test Cases Generalization for Autonomous Driving Object Detection Algorithms

    Jiang, Zhengmin / Liu, Jia / Sang, Ming et al. | IEEE | 2024


    Autonomous driving object detection and avoidance

    FUNKE JOSEPH / QIAN STEVEN CHENG / OKAMOTO KAZUHIDE et al. | Europäisches Patentamt | 2025

    Freier Zugriff