No Cover Image

Journal article 7 views

Dense Semantic Rerfinement Using Active Similarity Learning

Connor Clarkson, Michael G. Edwards, Xianghua Xie Orcid Logo

International Journal on Computer Science and Information Systems

Swansea University Authors: Connor Clarkson, Michael G. Edwards, Xianghua Xie Orcid Logo

Abstract

Defect detection has achieved state-of-the-art results in both localisation and classification of various types of defects, manufacturing domains is no exception to this. Just like in many areas of computer vision there is an assume of very high-quality datasets that have been verified by domain exp...

Full description

Published in: International Journal on Computer Science and Information Systems
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa66967
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-07-05T08:31:48Z
last_indexed 2024-07-05T08:31:48Z
id cronfa66967
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>66967</id><entry>2024-07-05</entry><title>Dense Semantic Rerfinement Using Active Similarity Learning</title><swanseaauthors><author><sid>e1a00716a3866cd4d8bb0ade1bada119</sid><firstname>Connor</firstname><surname>Clarkson</surname><name>Connor Clarkson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>8903caf3d43fca03602a72ed31d17c59</sid><firstname>Michael G.</firstname><surname>Edwards</surname><name>Michael G. Edwards</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-07-05</date><deptcode>MACS</deptcode><abstract>Defect detection has achieved state-of-the-art results in both localisation and classification of various types of defects, manufacturing domains is no exception to this. Just like in many areas of computer vision there is an assume of very high-quality datasets that have been verified by domain experts, however labelling such data has become an increasing problem as we require greater quantities of it. Within defect detection the variability and composite nature of defect characteristics makes this a time-consuming and interactionheavy task with great amount of expert effort. We propose a new acquisition function based on the similarity of defect properties for refining labels over time by showing the expert only the most required to be labelled. We also explore different ways in which the expert labels defects and how we should feed these new refinements back into the model for utilising new knowledge in an effortful way. We achieve this with a graphical interface that provides additional information as data gets refined into a dense segmentation, allowing for decision-making with uncertain areas of the image.</abstract><type>Journal Article</type><journal>International Journal on Computer Science and Information Systems</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Similarity Learning, Data Refinement, Active Learning, Defect Detection, Interactive, AcquisitionFunction</keywords><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>Funded by the EPSRC Centre for Doctoral Training in Enhancing Human Interactions and Collaborations with Data and Intelligence Driven Systems (EP/S021892/1)</funders><projectreference/><lastEdited>2024-07-05T09:31:48.3665794</lastEdited><Created>2024-07-05T09:28:45.1700937</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Connor</firstname><surname>Clarkson</surname><order>1</order></author><author><firstname>Michael G.</firstname><surname>Edwards</surname><order>2</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling v2 66967 2024-07-05 Dense Semantic Rerfinement Using Active Similarity Learning e1a00716a3866cd4d8bb0ade1bada119 Connor Clarkson Connor Clarkson true false 8903caf3d43fca03602a72ed31d17c59 Michael G. Edwards Michael G. Edwards true false b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2024-07-05 MACS Defect detection has achieved state-of-the-art results in both localisation and classification of various types of defects, manufacturing domains is no exception to this. Just like in many areas of computer vision there is an assume of very high-quality datasets that have been verified by domain experts, however labelling such data has become an increasing problem as we require greater quantities of it. Within defect detection the variability and composite nature of defect characteristics makes this a time-consuming and interactionheavy task with great amount of expert effort. We propose a new acquisition function based on the similarity of defect properties for refining labels over time by showing the expert only the most required to be labelled. We also explore different ways in which the expert labels defects and how we should feed these new refinements back into the model for utilising new knowledge in an effortful way. We achieve this with a graphical interface that provides additional information as data gets refined into a dense segmentation, allowing for decision-making with uncertain areas of the image. Journal Article International Journal on Computer Science and Information Systems Similarity Learning, Data Refinement, Active Learning, Defect Detection, Interactive, AcquisitionFunction 0 0 0 0001-01-01 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Funded by the EPSRC Centre for Doctoral Training in Enhancing Human Interactions and Collaborations with Data and Intelligence Driven Systems (EP/S021892/1) 2024-07-05T09:31:48.3665794 2024-07-05T09:28:45.1700937 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Connor Clarkson 1 Michael G. Edwards 2 Xianghua Xie 0000-0002-2701-8660 3
title Dense Semantic Rerfinement Using Active Similarity Learning
spellingShingle Dense Semantic Rerfinement Using Active Similarity Learning
Connor Clarkson
Michael G. Edwards
Xianghua Xie
title_short Dense Semantic Rerfinement Using Active Similarity Learning
title_full Dense Semantic Rerfinement Using Active Similarity Learning
title_fullStr Dense Semantic Rerfinement Using Active Similarity Learning
title_full_unstemmed Dense Semantic Rerfinement Using Active Similarity Learning
title_sort Dense Semantic Rerfinement Using Active Similarity Learning
author_id_str_mv e1a00716a3866cd4d8bb0ade1bada119
8903caf3d43fca03602a72ed31d17c59
b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv e1a00716a3866cd4d8bb0ade1bada119_***_Connor Clarkson
8903caf3d43fca03602a72ed31d17c59_***_Michael G. Edwards
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Connor Clarkson
Michael G. Edwards
Xianghua Xie
author2 Connor Clarkson
Michael G. Edwards
Xianghua Xie
format Journal article
container_title International Journal on Computer Science and Information Systems
institution Swansea University
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description Defect detection has achieved state-of-the-art results in both localisation and classification of various types of defects, manufacturing domains is no exception to this. Just like in many areas of computer vision there is an assume of very high-quality datasets that have been verified by domain experts, however labelling such data has become an increasing problem as we require greater quantities of it. Within defect detection the variability and composite nature of defect characteristics makes this a time-consuming and interactionheavy task with great amount of expert effort. We propose a new acquisition function based on the similarity of defect properties for refining labels over time by showing the expert only the most required to be labelled. We also explore different ways in which the expert labels defects and how we should feed these new refinements back into the model for utilising new knowledge in an effortful way. We achieve this with a graphical interface that provides additional information as data gets refined into a dense segmentation, allowing for decision-making with uncertain areas of the image.
published_date 0001-01-01T09:31:48Z
_version_ 1803727204755963904
score 11.01438

Similar Items