Learning non-linear reconstruction models for image set classification

Munawar Hayat, Mohammed Bennamoun, Senjian An

    Research output: Chapter in Book/Conference paperConference paper

    54 Citations (Scopus)

    Abstract

    © 2014 IEEE. We propose a deep learning framework for image set classification with application to face recognition. An Adaptive Deep Network Template (ADNT) is defined whose parameters are initialized by performing unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines (GRBMs). The pre-initialized ADNT is then separately trained for images of each class and class-specific models are learnt. Based on the minimum reconstruction error from the learnt class-specific models, a majority voting strategy is used for classification. The proposed framework is extensively evaluated for the task of image set classification based face recognition on Honda/UCSD, CMU Mobo, YouTube Celebrities and a Kinect dataset. Our experimental results and comparisons with existing state-of-the-art methods show that the proposed method consistently achieves the best performance on all these datasets.
    Original languageEnglish
    Title of host publication2014 IEEE Conference on Computer Vision and Pattern Recognition
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1915-1922
    ISBN (Print)9781479951178
    DOIs
    Publication statusPublished - 2014
    Event2014 IEEE Conference on Computer Vision and Pattern Recognition - USA, Columbus, United States
    Duration: 23 Jun 201428 Jun 2014
    Conference number: 114804

    Conference

    Conference2014 IEEE Conference on Computer Vision and Pattern Recognition
    Abbreviated titleCVPR
    CountryUnited States
    CityColumbus
    Period23/06/1428/06/14

    Fingerprint Dive into the research topics of 'Learning non-linear reconstruction models for image set classification'. Together they form a unique fingerprint.

    Cite this