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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Combining generative models and Fisher kernels for object recognition


    Contributors:
    Holub, A.D. (author) / Welling, M. (author) / Perona, P. (author)


    Publication date :

    2005-01-01


    Size :

    728450 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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


    Identifying Individuals in Video by Combining `Generative' and Discriminative Head Models

    Everingham, M. / Zisserman, A. / IEEE | British Library Conference Proceedings | 2005