Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in principle, superior performance, generative approaches provide many useful features, one of which is the ability to naturally establish explicit correspondence between model components and scene features - this, in turn, allows for the handling of missing data and unsupervised learning in clutter. We explore a hybrid generative/discriminative approach using 'Fisher kernels' by Jaakkola and Haussler (1999) which retains most of the desirable properties of generative methods, while increasing the classification performance through a discriminative setting. Furthermore, we demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular benchmarks, show strong performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Combining generative models and Fisher kernels for object recognition


    Beteiligte:
    Holub, A.D. (Autor:in) / Welling, M. (Autor:in) / Perona, P. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    728450 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Combining Generative Models and Fisher Kernels for Object Recognition

    Holub, A. / Welling, M. / Perona, P. et al. | British Library Conference Proceedings | 2005




    Object Detection Combining Recognition and Segmentation

    Wang, Liming / Shi, Jianbo / Song, Gang et al. | Springer Verlag | 2007


    Object Recognition by Combining Paraperspective Images

    Sugimoto, A. | British Library Online Contents | 1996