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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Sharing features: efficient boosting procedures for multiclass object detection


    Beteiligte:
    Torralba, A. (Autor:in) / Murphy, K.P. (Autor:in) / Freeman, W.T. (Autor:in)


    Erscheinungsdatum :

    01.01.2004


    Format / Umfang :

    738178 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    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

    Freier Zugriff


    MULTICLASS CONFIDENCE AND LOCALIZATION CALIBRATION FOR OBJECT DETECTION

    PATHIRAJA BIMSARA / GUNAWARDHANA MALITHA / KHAN MUHAMMAD HARIS | Europäisches Patentamt | 2025

    Freier Zugriff