Learning non-linear reconstruction models for image set classification

Munawar Hayat, Mohammed Bennamoun, Senjian An

Research output: A Conference proceeding or a Chapter in BookConference contribution

56 Citations (Scopus)
1 Downloads (Pure)

Abstract

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 publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
EditorsMunawar Hayat
Place of PublicationColumbus OH
PublisherIEEE
Pages1915-1922
Number of pages8
Volume1
ISBN (Electronic)9781479951178, 9781479951178
ISBN (Print)9781479951178
DOIs
Publication statusPublished - 23 Jun 2014
Externally publishedYes
Event2014 IEEE Conference on Computer Vision and Pattern Recognition - Columbus, Columbus, United States
Duration: 23 Jun 201428 Jun 2014

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference2014 IEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2014
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