Keep It Simple: Evaluating Local Search-Based Latent Space Editing

Semantic image editing allows users to selectively change entire image attributes in a controlled manner with just a few clicks. Most approaches use a generative adversarial network (GAN) for this task to learn an appropriate latent space representation and attribute-specific transformations. Attrib...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:SN computer science 2023-10, Vol.4 (6), p.820, Article 820
Hauptverfasser: Meißner, Andreas, Fröhlich, Andreas, Geierhos, Michaela
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 6
container_start_page 820
container_title SN computer science
container_volume 4
creator Meißner, Andreas
Fröhlich, Andreas
Geierhos, Michaela
description Semantic image editing allows users to selectively change entire image attributes in a controlled manner with just a few clicks. Most approaches use a generative adversarial network (GAN) for this task to learn an appropriate latent space representation and attribute-specific transformations. Attribute entanglement has been a limiting factor for previous approaches to attribute manipulation. However, more recent approaches have made significant improvements in this regard using separate networks for attribute extraction. Iterative optimization algorithms based on backpropagation can be used to find attribute vectors with minimal entanglement, but this requires large amounts of GPU memory, can lead to training instability, and requires differentiable models. To circumvent these issues, we present a local search-based approach to latent space editing that achieves comparable performance to existing algorithms while avoiding the aforementioned drawbacks. We also introduce a new evaluation metric that is easier to interpret than previous metrics.
doi_str_mv 10.1007/s42979-023-02272-4
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2921081323</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2921081323</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1594-7a0e5eade6b87f3740fa83c6190a469f34781cb5ceb86e1ecd3dd45cd8f49493</originalsourceid><addsrcrecordid>eNp9kE1Lw0AQhhdRsNT-AU8LnqOzH8nuerOlajHgob0v282kpqRJ3E0F_72pEfTkYZg5PO878BByzeCWAai7KLlRJgEuhuGKJ_KMTHiWsUQbUOd_7ksyi3EPADwFKbN0QuYviB1d9XRdHboa7-nyw9VH11fNjuatdzVdowv-LZm7iAXNXY_NAHfOI10W1Ym7IhelqyPOfvaUbB6Xm8Vzkr8-rRYPeeJZamSiHGCKrsBsq1UplITSaeEzZsDJzJRCKs38NvW41Rky9IUoCpn6QpfSSCOm5Gas7UL7fsTY2317DM3w0XLDGWgmuBgoPlI-tDEGLG0XqoMLn5aBPdmyoy072LLftqwcQmIMxQFudhh-q_9JfQEQHGsn</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2921081323</pqid></control><display><type>article</type><title>Keep It Simple: Evaluating Local Search-Based Latent Space Editing</title><source>ProQuest Central UK/Ireland</source><source>SpringerLink Journals - AutoHoldings</source><source>ProQuest Central</source><creator>Meißner, Andreas ; Fröhlich, Andreas ; Geierhos, Michaela</creator><creatorcontrib>Meißner, Andreas ; Fröhlich, Andreas ; Geierhos, Michaela</creatorcontrib><description>Semantic image editing allows users to selectively change entire image attributes in a controlled manner with just a few clicks. Most approaches use a generative adversarial network (GAN) for this task to learn an appropriate latent space representation and attribute-specific transformations. Attribute entanglement has been a limiting factor for previous approaches to attribute manipulation. However, more recent approaches have made significant improvements in this regard using separate networks for attribute extraction. Iterative optimization algorithms based on backpropagation can be used to find attribute vectors with minimal entanglement, but this requires large amounts of GPU memory, can lead to training instability, and requires differentiable models. To circumvent these issues, we present a local search-based approach to latent space editing that achieves comparable performance to existing algorithms while avoiding the aforementioned drawbacks. We also introduce a new evaluation metric that is easier to interpret than previous metrics.</description><identifier>ISSN: 2661-8907</identifier><identifier>ISSN: 2662-995X</identifier><identifier>EISSN: 2661-8907</identifier><identifier>DOI: 10.1007/s42979-023-02272-4</identifier><language>eng</language><publisher>Singapore: Springer Nature Singapore</publisher><subject>Advances on Computational Intelligence 2022 ; Algorithms ; Back propagation ; Computer Imaging ; Computer Science ; Computer Systems Organization and Communication Networks ; Data Structures and Information Theory ; Datasets ; Editing ; Entanglement ; Generative adversarial networks ; Information Systems and Communication Service ; Iterative methods ; Original Research ; Pattern Recognition and Graphics ; Semantics ; Software Engineering/Programming and Operating Systems ; Vision</subject><ispartof>SN computer science, 2023-10, Vol.4 (6), p.820, Article 820</ispartof><rights>The Author(s) 2023</rights><rights>The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1594-7a0e5eade6b87f3740fa83c6190a469f34781cb5ceb86e1ecd3dd45cd8f49493</cites><orcidid>0000-0002-8180-5606</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s42979-023-02272-4$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2921081323?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>314,780,784,21387,27923,27924,33743,41487,42556,43804,51318,64384,64388,72340</link.rule.ids></links><search><creatorcontrib>Meißner, Andreas</creatorcontrib><creatorcontrib>Fröhlich, Andreas</creatorcontrib><creatorcontrib>Geierhos, Michaela</creatorcontrib><title>Keep It Simple: Evaluating Local Search-Based Latent Space Editing</title><title>SN computer science</title><addtitle>SN COMPUT. SCI</addtitle><description>Semantic image editing allows users to selectively change entire image attributes in a controlled manner with just a few clicks. Most approaches use a generative adversarial network (GAN) for this task to learn an appropriate latent space representation and attribute-specific transformations. Attribute entanglement has been a limiting factor for previous approaches to attribute manipulation. However, more recent approaches have made significant improvements in this regard using separate networks for attribute extraction. Iterative optimization algorithms based on backpropagation can be used to find attribute vectors with minimal entanglement, but this requires large amounts of GPU memory, can lead to training instability, and requires differentiable models. To circumvent these issues, we present a local search-based approach to latent space editing that achieves comparable performance to existing algorithms while avoiding the aforementioned drawbacks. We also introduce a new evaluation metric that is easier to interpret than previous metrics.</description><subject>Advances on Computational Intelligence 2022</subject><subject>Algorithms</subject><subject>Back propagation</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Computer Systems Organization and Communication Networks</subject><subject>Data Structures and Information Theory</subject><subject>Datasets</subject><subject>Editing</subject><subject>Entanglement</subject><subject>Generative adversarial networks</subject><subject>Information Systems and Communication Service</subject><subject>Iterative methods</subject><subject>Original Research</subject><subject>Pattern Recognition and Graphics</subject><subject>Semantics</subject><subject>Software Engineering/Programming and Operating Systems</subject><subject>Vision</subject><issn>2661-8907</issn><issn>2662-995X</issn><issn>2661-8907</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp9kE1Lw0AQhhdRsNT-AU8LnqOzH8nuerOlajHgob0v282kpqRJ3E0F_72pEfTkYZg5PO878BByzeCWAai7KLlRJgEuhuGKJ_KMTHiWsUQbUOd_7ksyi3EPADwFKbN0QuYviB1d9XRdHboa7-nyw9VH11fNjuatdzVdowv-LZm7iAXNXY_NAHfOI10W1Ym7IhelqyPOfvaUbB6Xm8Vzkr8-rRYPeeJZamSiHGCKrsBsq1UplITSaeEzZsDJzJRCKs38NvW41Rky9IUoCpn6QpfSSCOm5Gas7UL7fsTY2317DM3w0XLDGWgmuBgoPlI-tDEGLG0XqoMLn5aBPdmyoy072LLftqwcQmIMxQFudhh-q_9JfQEQHGsn</recordid><startdate>20231021</startdate><enddate>20231021</enddate><creator>Meißner, Andreas</creator><creator>Fröhlich, Andreas</creator><creator>Geierhos, Michaela</creator><general>Springer Nature Singapore</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><orcidid>https://orcid.org/0000-0002-8180-5606</orcidid></search><sort><creationdate>20231021</creationdate><title>Keep It Simple: Evaluating Local Search-Based Latent Space Editing</title><author>Meißner, Andreas ; Fröhlich, Andreas ; Geierhos, Michaela</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1594-7a0e5eade6b87f3740fa83c6190a469f34781cb5ceb86e1ecd3dd45cd8f49493</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Advances on Computational Intelligence 2022</topic><topic>Algorithms</topic><topic>Back propagation</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Computer Systems Organization and Communication Networks</topic><topic>Data Structures and Information Theory</topic><topic>Datasets</topic><topic>Editing</topic><topic>Entanglement</topic><topic>Generative adversarial networks</topic><topic>Information Systems and Communication Service</topic><topic>Iterative methods</topic><topic>Original Research</topic><topic>Pattern Recognition and Graphics</topic><topic>Semantics</topic><topic>Software Engineering/Programming and Operating Systems</topic><topic>Vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Meißner, Andreas</creatorcontrib><creatorcontrib>Fröhlich, Andreas</creatorcontrib><creatorcontrib>Geierhos, Michaela</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><jtitle>SN computer science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Meißner, Andreas</au><au>Fröhlich, Andreas</au><au>Geierhos, Michaela</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Keep It Simple: Evaluating Local Search-Based Latent Space Editing</atitle><jtitle>SN computer science</jtitle><stitle>SN COMPUT. SCI</stitle><date>2023-10-21</date><risdate>2023</risdate><volume>4</volume><issue>6</issue><spage>820</spage><pages>820-</pages><artnum>820</artnum><issn>2661-8907</issn><issn>2662-995X</issn><eissn>2661-8907</eissn><abstract>Semantic image editing allows users to selectively change entire image attributes in a controlled manner with just a few clicks. Most approaches use a generative adversarial network (GAN) for this task to learn an appropriate latent space representation and attribute-specific transformations. Attribute entanglement has been a limiting factor for previous approaches to attribute manipulation. However, more recent approaches have made significant improvements in this regard using separate networks for attribute extraction. Iterative optimization algorithms based on backpropagation can be used to find attribute vectors with minimal entanglement, but this requires large amounts of GPU memory, can lead to training instability, and requires differentiable models. To circumvent these issues, we present a local search-based approach to latent space editing that achieves comparable performance to existing algorithms while avoiding the aforementioned drawbacks. We also introduce a new evaluation metric that is easier to interpret than previous metrics.</abstract><cop>Singapore</cop><pub>Springer Nature Singapore</pub><doi>10.1007/s42979-023-02272-4</doi><orcidid>https://orcid.org/0000-0002-8180-5606</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2661-8907
ispartof SN computer science, 2023-10, Vol.4 (6), p.820, Article 820
issn 2661-8907
2662-995X
2661-8907
language eng
recordid cdi_proquest_journals_2921081323
source ProQuest Central UK/Ireland; SpringerLink Journals - AutoHoldings; ProQuest Central
subjects Advances on Computational Intelligence 2022
Algorithms
Back propagation
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Datasets
Editing
Entanglement
Generative adversarial networks
Information Systems and Communication Service
Iterative methods
Original Research
Pattern Recognition and Graphics
Semantics
Software Engineering/Programming and Operating Systems
Vision
title Keep It Simple: Evaluating Local Search-Based Latent Space Editing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T12%3A43%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Keep%20It%20Simple:%20Evaluating%20Local%20Search-Based%20Latent%20Space%20Editing&rft.jtitle=SN%20computer%20science&rft.au=Mei%C3%9Fner,%20Andreas&rft.date=2023-10-21&rft.volume=4&rft.issue=6&rft.spage=820&rft.pages=820-&rft.artnum=820&rft.issn=2661-8907&rft.eissn=2661-8907&rft_id=info:doi/10.1007/s42979-023-02272-4&rft_dat=%3Cproquest_cross%3E2921081323%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2921081323&rft_id=info:pmid/&rfr_iscdi=true