By representing images and image prototypes by linear subspaces spanned by "tangent vectors" (derivatives of an image with respect to translation, rotation, etc.), impressive invariance to known types of uniform distortion can be built into feedforward discriminators. We describe a new probability model that can jointly cluster data and learn mixtures of nonuniform, smooth deformation fields. Our fields are based on low-frequency wavelets, so they use very few parameters to model a wide range of smooth deformations (unlike, e.g., factor analysis, which uses a large number of parameters to model deformations). In spirit, our ideas are most similar to the idea of separating content from style published by Tenenbaum and Freeman. However, our models do not need labeled data for training, and thus allow for unsupervised separation of appearance from deformation. We give results on handwritten digit recognition and face recognition.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Separating appearance from deformation


    Beteiligte:
    Jojic, N. (Autor:in) / Simard, P. (Autor:in) / Frey, B.J. (Autor:in) / Heckerman, D. (Autor:in)


    Erscheinungsdatum :

    01.01.2001


    Format / Umfang :

    900501 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Separating Appearance from Deformation

    Jojic, N. / Simard, P. / Frey, B. et al. | British Library Conference Proceedings | 2001


    Separating device and separating body combined device

    LI JINLING / REN TAN / ZHENG ZE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Appearance part plate, preparation method of appearance part plate, appearance part, forming process of appearance part and vehicle

    ZHOU HANMEI / LI LING / ZOU CHUANLI et al. | Europäisches Patentamt | 2025

    Freier Zugriff


    Separating gyroscopes from Greek sandwiches

    British Library Online Contents | 2005