Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn models from a set of training examples. Generative models learn their representations by considering data from a single class. Generative models are popular in computer vision for many reasons, including their ability to elegantly incorporate prior knowledge and to handle correspondences between object parts and detected features. However, generative models are often inferior to discriminative models during classification tasks. We study a discriminative approach to learning object categories which maintains the representational power of generative learning, but trains the generative models in a discriminative manner. The discriminatively trained models perform better during classification tasks as a result of selecting discriminative sets of features. We conclude by proposing a multi-class object recognition system which initially trains object classes in a generative manner, identifies subsets of similar classes with high confusion, and finally trains models for these subsets in a discriminative manner to realize gains in classification performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A discriminative framework for modelling object classes


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


    Publication date :

    2005-01-01


    Size :

    1107396 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification

    Yan, R. / Zhang, J. / Yang, J. et al. | British Library Conference Proceedings | 2004



    Object recognition using discriminative parts

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



    Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification

    Kumar, S. / Hebert, M. / IEEE | British Library Conference Proceedings | 2003