Learning non-linear reconstruction models for image set classification

© 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 Boltzman...

Full description

Bibliographic Details
Main Authors: Hayat, M., Bennamoun, M., An, Senjian
Format: Conference Paper
Published: 2014
Online Access:http://hdl.handle.net/20.500.11937/69852
_version_ 1848762150146801664
author Hayat, M.
Bennamoun, M.
An, Senjian
author_facet Hayat, M.
Bennamoun, M.
An, Senjian
author_sort Hayat, M.
building Curtin Institutional Repository
collection Online Access
description © 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.
first_indexed 2025-11-14T10:42:59Z
format Conference Paper
id curtin-20.500.11937-69852
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:42:59Z
publishDate 2014
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-698522018-08-08T04:56:39Z Learning non-linear reconstruction models for image set classification Hayat, M. Bennamoun, M. An, Senjian © 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. 2014 Conference Paper http://hdl.handle.net/20.500.11937/69852 10.1109/CVPR.2014.246 restricted
spellingShingle Hayat, M.
Bennamoun, M.
An, Senjian
Learning non-linear reconstruction models for image set classification
title Learning non-linear reconstruction models for image set classification
title_full Learning non-linear reconstruction models for image set classification
title_fullStr Learning non-linear reconstruction models for image set classification
title_full_unstemmed Learning non-linear reconstruction models for image set classification
title_short Learning non-linear reconstruction models for image set classification
title_sort learning non-linear reconstruction models for image set classification
url http://hdl.handle.net/20.500.11937/69852