We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a multi-class boosting procedure (joint boosting) that reduces both the computational and sample complexity, by finding common features that can be shared across the classes. The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required is observed to scale approximately logarithmically with the number of classes. In addition, we find that the features selected by independently trained classifiers are often specific to the class, whereas the features selected by the jointly trained classifiers are more generic features, such as lines and edges.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Sharing features: efficient boosting procedures for multiclass object detection


    Contributors:
    Torralba, A. (author) / Murphy, K.P. (author) / Freeman, W.T. (author)


    Publication date :

    2004-01-01


    Size :

    738178 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection

    Torralba, A. / Murphy, K. / Freeman, W. et al. | British Library Conference Proceedings | 2004



    Orientation invariant features for multiclass object recognition

    Villamizar, Michael / Sanfeliu, Alberto / Andrade-Cetto, Juan | BASE | 2006

    Free access


    Boosting histograms of descriptor distances for scalable multiclass specific scene recognition

    Chin, T. J. / Suter, D. / Wang, H. | British Library Online Contents | 2011