Few-shot object detection is a challenging task because of the limited annotation data. Under the limitation of few-shot samples, images from the same class may differ significantly in appearance and pose. Although the research has progressed considerably since adding the prototype vector to few-shot object detection, the previous paradigm is still constrained by several factors: (1) using a single prototype to represent the support image tends to cause semantic ambiguity; (2) the way of extracting prototypes is too simple, like global average pooling, which makes prototypes not representative enough. In this work, we design PMR-CNN to address the above limitations. PMR-CNN proposes a new method of prototype generation and enhances the representative information by using multiple prototypes to represent support images. For experiments, we not only evaluate our method on general image dataset MS COCO, but also evaluate on SiTi (a real-world autonomous driving dataset collected by us). Experiment on the few-shot object detection benchmark shows that we have a significant advantage over the previous methods. Code is available at: https://github.com/Chientsung-Chou/PMR-CNN.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    PMR-CNN: Prototype Mixture R-CNN for Few-Shot Object Detection


    Beteiligte:
    Zhou, Jiancong (Autor:in) / Mei, Jilin (Autor:in) / Li, Haoyu (Autor:in) / Hu, Yu (Autor:in)


    Erscheinungsdatum :

    2023-06-04


    Format / Umfang :

    17696516 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Any-Shot Object Detection

    Rahman, Shafin / Khan, Salman / Barnes, Nick et al. | British Library Conference Proceedings | 2021


    Object Level Frame Comparison for Video Shot Detection

    Vadivel, A. / Mohan, M. / Sural, Shamik et al. | IEEE | 2005


    Background Learnable Cascade for Zero-Shot Object Detection

    Zheng, Ye / Huang, Ruoran / Han, Chuanqi et al. | British Library Conference Proceedings | 2021


    Few-shot Small Object Detection in Predictable Background

    Deng, Lingzhu / Dong, Ziqi / Sui, Yunfeng et al. | IEEE | 2023