Reverse training: An efficient approach for image set classification

This paper introduces a new approach, called reverse training, to efficiently extend binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers, the proposed approach is very efficient...

Full description

Bibliographic Details
Main Authors: Hayat, M., Bennamoun, M., An, Senjian
Format: Conference Paper
Published: 2014
Online Access:http://hdl.handle.net/20.500.11937/69531
_version_ 1848762065478483968
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 This paper introduces a new approach, called reverse training, to efficiently extend binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers, the proposed approach is very efficient since it trains a single binary classifier to optimally discriminate the class of the query image set from all others. For this purpose, the classifier is trained with the images of the query set (labelled positive) and a randomly sampled subset of the training data (labelled negative). The trained classifier is then evaluated on rest of the training images. The class of these images with their largest percentage classified as positive is predicted as the class of the query image set. The confidence level of the prediction is also computed and integrated into the proposed approach to further enhance its robustness and accuracy. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for face and object recognition on a number of datasets. © 2014 Springer International Publishing.
first_indexed 2025-11-14T10:41:38Z
format Conference Paper
id curtin-20.500.11937-69531
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:41:38Z
publishDate 2014
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-695312018-08-08T04:56:25Z Reverse training: An efficient approach for image set classification Hayat, M. Bennamoun, M. An, Senjian This paper introduces a new approach, called reverse training, to efficiently extend binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers, the proposed approach is very efficient since it trains a single binary classifier to optimally discriminate the class of the query image set from all others. For this purpose, the classifier is trained with the images of the query set (labelled positive) and a randomly sampled subset of the training data (labelled negative). The trained classifier is then evaluated on rest of the training images. The class of these images with their largest percentage classified as positive is predicted as the class of the query image set. The confidence level of the prediction is also computed and integrated into the proposed approach to further enhance its robustness and accuracy. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for face and object recognition on a number of datasets. © 2014 Springer International Publishing. 2014 Conference Paper http://hdl.handle.net/20.500.11937/69531 10.1007/978-3-319-10599-4_50 restricted
spellingShingle Hayat, M.
Bennamoun, M.
An, Senjian
Reverse training: An efficient approach for image set classification
title Reverse training: An efficient approach for image set classification
title_full Reverse training: An efficient approach for image set classification
title_fullStr Reverse training: An efficient approach for image set classification
title_full_unstemmed Reverse training: An efficient approach for image set classification
title_short Reverse training: An efficient approach for image set classification
title_sort reverse training: an efficient approach for image set classification
url http://hdl.handle.net/20.500.11937/69531