We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (learning object classes with unsupervised segmentation) which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and pose. A key aspect of this model is that the object appearance is allowed to vary from image to image, allowing for significant within-class variation. By iteratively updating the belief in the object's position, size, segmentation and pose, LOCUS avoids making hard decisions about any of these quantities and so allows for each to be refined at any stage. We show that LOCUS successfully learns an object class model from unlabeled images, whilst also giving segmentation accuracies that rival existing supervised methods. Finally, we demonstrate simultaneous recognition and segmentation in novel images using the learned models for a number of object classes, as well as unsupervised object discovery and tracking in video.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    LOCUS: learning object classes with unsupervised segmentation


    Beteiligte:
    Winn, J. (Autor:in) / Jojic, N. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    933969 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LOCUS: Learning Object Classes with Unsupervised Segmentation

    Winn, J. / Jojic, N. / IEEE | British Library Conference Proceedings | 2005


    Object tracking by unsupervised learning

    WYFFELS KEVIN | Europäisches Patentamt | 2019

    Freier Zugriff

    OBJECT TRACKING BY UNSUPERVISED LEARNING

    WYFFELS KEVIN | Europäisches Patentamt | 2018

    Freier Zugriff

    OBJECT TRACKING BY UNSUPERVISED LEARNING

    WYFFELS KEVIN | Europäisches Patentamt | 2018

    Freier Zugriff

    Object tracking by unsupervised learning

    WYFFELS KEVIN | Europäisches Patentamt | 2019

    Freier Zugriff