The performance of image retrieval with SVM active learning is known to be poor when started with few labeled images only. In this paper, the problem is solved by incorporating the unlabelled images into the bootstrapping of the learning process. In this work, the initial SVM classifier is trained with the few labeled images and the unlabelled images randomly selected from the image database. Both theoretical analysis and experimental results show that by incorporating unlabelled images in the bootstrapping, the efficiency of SVM active learning can be improved, and thus improves the overall retrieval performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Bootstrapping SVM active learning by incorporating unlabelled images for image retrieval


    Beteiligte:
    Lei Wang, (Autor:in) / Kap Luk Chan, (Autor:in) / Zhihua Zhang, (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    2797509 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Bootstrapping SVM Active Learning by Incorporating Unlabelled Images for Image Retrieval

    Wang, L. / Chan, K. / Zhang, Z. et al. | British Library Conference Proceedings | 2003


    Learning with constrained and unlabelled data

    Lange, T. / Law, M.H.C. / Jain, A.K. et al. | IEEE | 2005


    New Unlabelled Process Oils for the Tyre and Rubber Industry

    Wadie, J. | British Library Conference Proceedings | 1999


    Stochastic exploration and active learning for image retrieval

    Cord, M. / Gosselin, P. H. / Philipp-Foliguet, S. | British Library Online Contents | 2007


    Incremental learning for bootstrapping object classifier models

    Karaoguz, Cem / Gepperth, Alexander | IEEE | 2016