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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Separating appearance from deformation


    Contributors:
    Jojic, N. (author) / Simard, P. (author) / Frey, B.J. (author) / Heckerman, D. (author)


    Publication date :

    2001-01-01


    Size :

    900501 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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. | European Patent Office | 2024

    Free access


    Separating gyroscopes from Greek sandwiches

    British Library Online Contents | 2005