Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this paper we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining them.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Generative versus discriminative methods for object recognition


    Contributors:
    Ulusoy, I. (author) / Bishop, C.M. (author)


    Publication date :

    2005-01-01


    Size :

    496034 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object recognition using discriminative parts

    Liu, Y. H. / Lee, A. J. / Chang, F. | British Library Online Contents | 2012


    A Hybrid Generative-Discriminative Learning Algorithm for Image Recognition

    Wang, Bin / Li, Chuanjiang / Li, Xiong et al. | Springer Verlag | 2017



    Hybrid Generative-Discriminative Visual Categorization

    Holub, A. D. / Welling, M. / Perona, P. | British Library Online Contents | 2008


    Monitoring of facial stress during space flight: Optical computer recognition combining discriminative and generative methods

    Dinges, D. F. / Venkataraman, S. / McGlinchey, E. L. et al. | British Library Conference Proceedings | 2007