No Cover Image

Conference contribution 246 views

A Deep Convolutional Auto-Encoder with Embedded Clustering / A. Alqahtani; X. Xie; J. Deng; M.W. Jones

2018 25th IEEE International Conference on Image Processing (ICIP), Pages: 4058 - 4062

Swansea University Author: Jones, Mark

  • Accepted Manuscript under embargo until: 6th September 2019

Abstract

In this paper, we propose a clustering approach embedded in a deep convolutional auto-encoder (DCAE). In contrast to conventional clustering approaches, our method simultaneously learns feature representations and cluster assignments through DCAEs. DCAEs have been effective in image processing as it...

Full description

Published in: 2018 25th IEEE International Conference on Image Processing (ICIP)
ISBN: 978-1-4799-7062-9 978-1-4799-7061-2
ISSN: 2381-8549
Published: Megaron Athens International Conference Centre, Athens, Greece 25th IEEE International Conference on Image Processing (ICIP) 2018
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa40682
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-06-08T13:30:11Z
last_indexed 2019-03-29T12:26:33Z
id cronfa40682
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-03-28T12:53:26Z</datestamp><bib-version>v2</bib-version><id>40682</id><entry>2018-06-08</entry><title>A Deep Convolutional Auto-Encoder with Embedded Clustering</title><alternativeTitle></alternativeTitle><author>Mark Jones</author><firstname>Mark</firstname><surname>Jones</surname><active>true</active><ORCID>0000-0001-8991-1190</ORCID><ethesisStudent>false</ethesisStudent><sid>2e1030b6e14fc9debd5d5ae7cc335562</sid><email>dda0c29127c698255a4c2b822dd94125</email><emailaddr>uiPdnV+XNibOpUxFjI3lXQgr5y2nBRz3haj4DmVVDsQ=</emailaddr><date>2018-06-08</date><deptcode>SCS</deptcode><abstract>In this paper, we propose a clustering approach embedded in a deep convolutional auto-encoder (DCAE). In contrast to conventional clustering approaches, our method simultaneously learns feature representations and cluster assignments through DCAEs. DCAEs have been effective in image processing as it fully utilizes the properties of convolutional neural networks. Our method consists of clustering and reconstruction objective functions. All data points are assigned to their new corresponding cluster centers during the optimization, after that, clustering centers are iteratively updated to obtain a stable performance of clustering. The experimental results on the MNIST dataset show that the proposed method substantially outperforms deep clustering models in term of clustering quality.</abstract><type>Conference contribution</type><journal>2018 25th IEEE International Conference on Image Processing (ICIP)</journal><volume/><journalNumber/><paginationStart>4058</paginationStart><paginationEnd>4062</paginationEnd><publisher>25th IEEE International Conference on Image Processing (ICIP)</publisher><placeOfPublication>Megaron Athens International Conference Centre, Athens, Greece</placeOfPublication><isbnPrint>978-1-4799-7062-9</isbnPrint><isbnElectronic>978-1-4799-7061-2</isbnElectronic><issnPrint/><issnElectronic>2381-8549</issnElectronic><keywords>Deep Learning, Deep Convolutional Auto-Encoder, Embedded Clustering</keywords><publishedDay>7</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2018</publishedYear><publishedDate>2018-10-07</publishedDate><doi>10.1109/ICIP.2018.8451506</doi><url>https://ieeexplore.ieee.org/document/8451506</url><notes></notes><college>College of Science</college><department>Computer Science</department><CollegeCode>CSCI</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution/><researchGroup>Visual Computing</researchGroup><supervisor/><sponsorsfunders/><grantnumber/><degreelevel/><degreename>None</degreename><lastEdited>2019-03-28T12:53:26Z</lastEdited><Created>2018-06-08T12:33:46Z</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>A.</firstname><surname>Alqahtani</surname><orcid/><order>1</order></author><author><firstname>X.</firstname><surname>Xie</surname><orcid/><order>2</order></author><author><firstname>J.</firstname><surname>Deng</surname><orcid/><order>3</order></author><author><firstname>M.W.</firstname><surname>Jones</surname><orcid/><order>4</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2018-06-08T12:37:41Z</uploaded><type>Output</type><contentLength>773745</contentLength><contentType>application/pdf</contentType><version>AM</version><cronfaStatus>true</cronfaStatus><action>Updated Notes</action><actionDate>28/03/2019</actionDate><embargoDate>2019-09-06T00:00:00</embargoDate><documentNotes>&#xA9; 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents></rfc1807>
spelling 2019-03-28T12:53:26Z v2 40682 2018-06-08 A Deep Convolutional Auto-Encoder with Embedded Clustering Mark Jones Mark Jones true 0000-0001-8991-1190 false 2e1030b6e14fc9debd5d5ae7cc335562 dda0c29127c698255a4c2b822dd94125 uiPdnV+XNibOpUxFjI3lXQgr5y2nBRz3haj4DmVVDsQ= 2018-06-08 SCS In this paper, we propose a clustering approach embedded in a deep convolutional auto-encoder (DCAE). In contrast to conventional clustering approaches, our method simultaneously learns feature representations and cluster assignments through DCAEs. DCAEs have been effective in image processing as it fully utilizes the properties of convolutional neural networks. Our method consists of clustering and reconstruction objective functions. All data points are assigned to their new corresponding cluster centers during the optimization, after that, clustering centers are iteratively updated to obtain a stable performance of clustering. The experimental results on the MNIST dataset show that the proposed method substantially outperforms deep clustering models in term of clustering quality. Conference contribution 2018 25th IEEE International Conference on Image Processing (ICIP) 4058 4062 25th IEEE International Conference on Image Processing (ICIP) Megaron Athens International Conference Centre, Athens, Greece 978-1-4799-7062-9 978-1-4799-7061-2 2381-8549 Deep Learning, Deep Convolutional Auto-Encoder, Embedded Clustering 7 10 2018 2018-10-07 10.1109/ICIP.2018.8451506 https://ieeexplore.ieee.org/document/8451506 College of Science Computer Science CSCI SCS Visual Computing None 2019-03-28T12:53:26Z 2018-06-08T12:33:46Z College of Science Computer Science A. Alqahtani 1 X. Xie 2 J. Deng 3 M.W. Jones 4 Under embargo Under embargo 2018-06-08T12:37:41Z Output 773745 application/pdf AM true Updated Notes 28/03/2019 2019-09-06T00:00:00 © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. true eng
title A Deep Convolutional Auto-Encoder with Embedded Clustering
spellingShingle A Deep Convolutional Auto-Encoder with Embedded Clustering
Jones, Mark
title_short A Deep Convolutional Auto-Encoder with Embedded Clustering
title_full A Deep Convolutional Auto-Encoder with Embedded Clustering
title_fullStr A Deep Convolutional Auto-Encoder with Embedded Clustering
title_full_unstemmed A Deep Convolutional Auto-Encoder with Embedded Clustering
title_sort A Deep Convolutional Auto-Encoder with Embedded Clustering
author_id_str_mv 2e1030b6e14fc9debd5d5ae7cc335562
author_id_fullname_str_mv 2e1030b6e14fc9debd5d5ae7cc335562_***_Jones, Mark
author Jones, Mark
author2 A. Alqahtani
X. Xie
J. Deng
M.W. Jones
format Conference contribution
container_title 2018 25th IEEE International Conference on Image Processing (ICIP)
container_start_page 4058
publishDate 2018
institution Swansea University
isbn 978-1-4799-7062-9
978-1-4799-7061-2
issn 2381-8549
doi_str_mv 10.1109/ICIP.2018.8451506
publisher 25th IEEE International Conference on Image Processing (ICIP)
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
url https://ieeexplore.ieee.org/document/8451506
document_store_str 0
active_str 1
researchgroup_str Visual Computing
description In this paper, we propose a clustering approach embedded in a deep convolutional auto-encoder (DCAE). In contrast to conventional clustering approaches, our method simultaneously learns feature representations and cluster assignments through DCAEs. DCAEs have been effective in image processing as it fully utilizes the properties of convolutional neural networks. Our method consists of clustering and reconstruction objective functions. All data points are assigned to their new corresponding cluster centers during the optimization, after that, clustering centers are iteratively updated to obtain a stable performance of clustering. The experimental results on the MNIST dataset show that the proposed method substantially outperforms deep clustering models in term of clustering quality.
published_date 2018-10-07T06:02:10Z
_version_ 1642451415565598720
score 10.836305