Source-free domain adaptive object detection (source-free DAOD) seeks to adapt a detector pre-trained on a source domain to an unlabeled target domain without requiring access to annotated source domain data. To address challenges posed by domain shifts, current source-free DAOD approaches mainly rely on the self-training paradigm, where pseudo labels are predicted and employed to fine-tune the detector on unlabeled target domain. However, these methods often encounter issues related to intra-class variation, resulting in category-specific biases and noisy pseudo labels. In response, we present an effective Multi-Prototype Guided source-free DAOD method, dubbed MPG, consisting of two key components: multi-prototype guided pseudo labeling (MPPL) and multi-prototype guided consistency regularization (MPCR) modules. In the MPPL module, we construct category-specific multiple prototypes to better represent the category with intra-class variations. Specifically, multiple prototypes with adaptive cluster centroids are introduced for each category to effectively capture the intra-class variations. Through the implementation of the proposed MPPL module, we derive more accurate pseudo labels by assessing the proximity of instance features to multiple category prototypes. In the MPCR module, we introduce multi-level consistency regularization, including prototype-based consistency and prediction consistency, which encourages the model to overlook style perturbations and learn domain-invariant representations. Extensive experiments on five public driving datasets demonstrate that MPG outperforms existing state-of-the-art methods, showcasing its effectiveness in adapting object detectors to target domains.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-Prototype Guided Source-Free Domain Adaptive Object Detection for Autonomous Driving


    Beteiligte:
    Zhang, Siqi (Autor:in) / Zhang, Lu (Autor:in) / Li, Guangsen (Autor:in) / Li, Pengcheng (Autor:in) / Liu, Zhiyong (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.01.2024


    Format / Umfang :

    4440040 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Autonomous Driving Object Detection Platform

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


    Object Detection for Autonomous Guided Vehicle

    Bhosale, Tanmay / Attar, Ajim / Warang, Prathamesh et al. | BASE | 2022

    Freier Zugriff


    Multi-sensor fusion 3D object detection for autonomous driving

    Alaba, Simegnew Yihunie / Ball, John E. | British Library Conference Proceedings | 2023


    AUTONOMOUS DRIVING OBJECT DETECTION AND AVOIDANCE

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

    Freier Zugriff