We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large and not known during training, and where the number of training samples for a single category is very small. The idea is to learn a function that maps input patterns into a target space such that the L/sub 1/ norm in the target space approximates the "semantic" distance in the input space. The method is applied to a face verification task. The learning process minimizes a discriminative loss function that drives the similarity metric to be small for pairs of faces from the same person, and large for pairs from different persons. The mapping from raw to the target space is a convolutional network whose architecture is designed for robustness to geometric distortions. The system is tested on the Purdue/AR face database which has a very high degree of variability in the pose, lighting, expression, position, and artificial occlusions such as dark glasses and obscuring scarves.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning a similarity metric discriminatively, with application to face verification


    Beteiligte:
    Chopra, S. (Autor:in) / Hadsell, R. (Autor:in) / LeCun, Y. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    600976 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Set2Model networks: Learning discriminatively to learn generative models

    Vakhitov, Alexander / Kuzmin, Andrey / Lempitsky, Victor | British Library Online Contents | 2018


    Discriminatively Learned Hierarchical Rank Pooling Networks

    Fernando, B. / Gould, S. | British Library Online Contents | 2017


    Vehicle detection using discriminatively trained part templates with variable size

    Niknejad, Hossein Tehrani / Kawano, Taiki / Shimizu, Mikio et al. | IEEE | 2012


    Vehicle Detection Using Discriminatively Trained Part Templates with Variable Size

    Tehrani Nik Nejad, H. / Kawano, T. / Mita, S. et al. | British Library Conference Proceedings | 2012