Discriminative transfer learning via local and global structure preservation
The current success of supervised learning is limited on large amounts of labeled training data. Transfer learning aims to learn an adaptive classifier for the unlabeled target domain data from the labeled source domain data, which is sampled from diverse probability distributions under changing con...
Gespeichert in:
Veröffentlicht in: | Signal, image and video processing image and video processing, 2019-06, Vol.13 (4), p.753-760 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 760 |
---|---|
container_issue | 4 |
container_start_page | 753 |
container_title | Signal, image and video processing |
container_volume | 13 |
creator | Wang, Chao Tuo, Hongya Wang, Jiexin Qiao, Lingfeng |
description | The current success of supervised learning is limited on large amounts of labeled training data. Transfer learning aims to learn an adaptive classifier for the unlabeled target domain data from the labeled source domain data, which is sampled from diverse probability distributions under changing conditions. Most previous works focus on how to reduce the distribution discrepancy between two involved domains, or exploit the shared common feature by preserving the local geometric structure of samples. In this paper, we propose a modified method jointly optimizing the local and global structure preservation. The main idea is to explore common features with manifold regularization. Discriminative repulsive force model is used to improve maximum mean discrepancy, which keeps discriminative property in the local sense via labeled source domain data and alleviates the global distribution discrepancy of the different domains. Quantitative results indicate that our method performs better than other methods on 16 cross-domain experiments. |
doi_str_mv | 10.1007/s11760-018-1405-7 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2219656565</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2219656565</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-1d10ee6df42f329a58217218ceb4b53a159a0d517ee932a41a0c5b73f5a27b753</originalsourceid><addsrcrecordid>eNp1kE9PwzAMxSMEEtPYB-AWiXMhTpqmPaLxZ0iTuMA5clN36lTSkbST-PZkKoIT9sHv8H62_Bi7BnELQpi7CGAKkQkoM8iFzswZW0BZqAwMwPmvFuqSrWLci1RKmrIoF2z70EUXuo_O49gdiY8BfWwp8J4w-M7v-LFD3g8Oe46-4bt-qJOMY5jcOAXih0CRwjHRg79iFy32kVY_c8nenx7f1pts-_r8sr7fZk5BMWbQgCAqmjaXrZIV6lKCkVA6qvNaKwRdoWg0GKJKScwBhdO1Ua1GaWqj1ZLdzHsPYficKI52P0zBp5NWSqgKferkgtnlwhBjoNYe0qMYviwIe8rNzrnZlJs95WZNYuTMxOT1Owp_m_-HvgGKEXAU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2219656565</pqid></control><display><type>article</type><title>Discriminative transfer learning via local and global structure preservation</title><source>SpringerLink Journals - AutoHoldings</source><creator>Wang, Chao ; Tuo, Hongya ; Wang, Jiexin ; Qiao, Lingfeng</creator><creatorcontrib>Wang, Chao ; Tuo, Hongya ; Wang, Jiexin ; Qiao, Lingfeng</creatorcontrib><description>The current success of supervised learning is limited on large amounts of labeled training data. Transfer learning aims to learn an adaptive classifier for the unlabeled target domain data from the labeled source domain data, which is sampled from diverse probability distributions under changing conditions. Most previous works focus on how to reduce the distribution discrepancy between two involved domains, or exploit the shared common feature by preserving the local geometric structure of samples. In this paper, we propose a modified method jointly optimizing the local and global structure preservation. The main idea is to explore common features with manifold regularization. Discriminative repulsive force model is used to improve maximum mean discrepancy, which keeps discriminative property in the local sense via labeled source domain data and alleviates the global distribution discrepancy of the different domains. Quantitative results indicate that our method performs better than other methods on 16 cross-domain experiments.</description><identifier>ISSN: 1863-1703</identifier><identifier>EISSN: 1863-1711</identifier><identifier>DOI: 10.1007/s11760-018-1405-7</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Computer Imaging ; Computer Science ; Data transfer (computers) ; Domains ; Image Processing and Computer Vision ; Multimedia Information Systems ; Original Paper ; Pattern Recognition and Graphics ; Preservation ; Regularization ; Signal,Image and Speech Processing ; Supervised learning ; Vision</subject><ispartof>Signal, image and video processing, 2019-06, Vol.13 (4), p.753-760</ispartof><rights>Springer-Verlag London Ltd., part of Springer Nature 2018</rights><rights>Copyright Springer Nature B.V. 2019</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-1d10ee6df42f329a58217218ceb4b53a159a0d517ee932a41a0c5b73f5a27b753</citedby><cites>FETCH-LOGICAL-c316t-1d10ee6df42f329a58217218ceb4b53a159a0d517ee932a41a0c5b73f5a27b753</cites><orcidid>0000-0002-3284-3673</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/s11760-018-1405-7$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11760-018-1405-7$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Wang, Chao</creatorcontrib><creatorcontrib>Tuo, Hongya</creatorcontrib><creatorcontrib>Wang, Jiexin</creatorcontrib><creatorcontrib>Qiao, Lingfeng</creatorcontrib><title>Discriminative transfer learning via local and global structure preservation</title><title>Signal, image and video processing</title><addtitle>SIViP</addtitle><description>The current success of supervised learning is limited on large amounts of labeled training data. Transfer learning aims to learn an adaptive classifier for the unlabeled target domain data from the labeled source domain data, which is sampled from diverse probability distributions under changing conditions. Most previous works focus on how to reduce the distribution discrepancy between two involved domains, or exploit the shared common feature by preserving the local geometric structure of samples. In this paper, we propose a modified method jointly optimizing the local and global structure preservation. The main idea is to explore common features with manifold regularization. Discriminative repulsive force model is used to improve maximum mean discrepancy, which keeps discriminative property in the local sense via labeled source domain data and alleviates the global distribution discrepancy of the different domains. Quantitative results indicate that our method performs better than other methods on 16 cross-domain experiments.</description><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Data transfer (computers)</subject><subject>Domains</subject><subject>Image Processing and Computer Vision</subject><subject>Multimedia Information Systems</subject><subject>Original Paper</subject><subject>Pattern Recognition and Graphics</subject><subject>Preservation</subject><subject>Regularization</subject><subject>Signal,Image and Speech Processing</subject><subject>Supervised learning</subject><subject>Vision</subject><issn>1863-1703</issn><issn>1863-1711</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1kE9PwzAMxSMEEtPYB-AWiXMhTpqmPaLxZ0iTuMA5clN36lTSkbST-PZkKoIT9sHv8H62_Bi7BnELQpi7CGAKkQkoM8iFzswZW0BZqAwMwPmvFuqSrWLci1RKmrIoF2z70EUXuo_O49gdiY8BfWwp8J4w-M7v-LFD3g8Oe46-4bt-qJOMY5jcOAXih0CRwjHRg79iFy32kVY_c8nenx7f1pts-_r8sr7fZk5BMWbQgCAqmjaXrZIV6lKCkVA6qvNaKwRdoWg0GKJKScwBhdO1Ua1GaWqj1ZLdzHsPYficKI52P0zBp5NWSqgKferkgtnlwhBjoNYe0qMYviwIe8rNzrnZlJs95WZNYuTMxOT1Owp_m_-HvgGKEXAU</recordid><startdate>20190601</startdate><enddate>20190601</enddate><creator>Wang, Chao</creator><creator>Tuo, Hongya</creator><creator>Wang, Jiexin</creator><creator>Qiao, Lingfeng</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-3284-3673</orcidid></search><sort><creationdate>20190601</creationdate><title>Discriminative transfer learning via local and global structure preservation</title><author>Wang, Chao ; Tuo, Hongya ; Wang, Jiexin ; Qiao, Lingfeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-1d10ee6df42f329a58217218ceb4b53a159a0d517ee932a41a0c5b73f5a27b753</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Data transfer (computers)</topic><topic>Domains</topic><topic>Image Processing and Computer Vision</topic><topic>Multimedia Information Systems</topic><topic>Original Paper</topic><topic>Pattern Recognition and Graphics</topic><topic>Preservation</topic><topic>Regularization</topic><topic>Signal,Image and Speech Processing</topic><topic>Supervised learning</topic><topic>Vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Chao</creatorcontrib><creatorcontrib>Tuo, Hongya</creatorcontrib><creatorcontrib>Wang, Jiexin</creatorcontrib><creatorcontrib>Qiao, Lingfeng</creatorcontrib><collection>CrossRef</collection><jtitle>Signal, image and video processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Chao</au><au>Tuo, Hongya</au><au>Wang, Jiexin</au><au>Qiao, Lingfeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Discriminative transfer learning via local and global structure preservation</atitle><jtitle>Signal, image and video processing</jtitle><stitle>SIViP</stitle><date>2019-06-01</date><risdate>2019</risdate><volume>13</volume><issue>4</issue><spage>753</spage><epage>760</epage><pages>753-760</pages><issn>1863-1703</issn><eissn>1863-1711</eissn><abstract>The current success of supervised learning is limited on large amounts of labeled training data. Transfer learning aims to learn an adaptive classifier for the unlabeled target domain data from the labeled source domain data, which is sampled from diverse probability distributions under changing conditions. Most previous works focus on how to reduce the distribution discrepancy between two involved domains, or exploit the shared common feature by preserving the local geometric structure of samples. In this paper, we propose a modified method jointly optimizing the local and global structure preservation. The main idea is to explore common features with manifold regularization. Discriminative repulsive force model is used to improve maximum mean discrepancy, which keeps discriminative property in the local sense via labeled source domain data and alleviates the global distribution discrepancy of the different domains. Quantitative results indicate that our method performs better than other methods on 16 cross-domain experiments.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s11760-018-1405-7</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-3284-3673</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1863-1703 |
ispartof | Signal, image and video processing, 2019-06, Vol.13 (4), p.753-760 |
issn | 1863-1703 1863-1711 |
language | eng |
recordid | cdi_proquest_journals_2219656565 |
source | SpringerLink Journals - AutoHoldings |
subjects | Computer Imaging Computer Science Data transfer (computers) Domains Image Processing and Computer Vision Multimedia Information Systems Original Paper Pattern Recognition and Graphics Preservation Regularization Signal,Image and Speech Processing Supervised learning Vision |
title | Discriminative transfer learning via local and global structure preservation |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A13%3A03IST&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=Discriminative%20transfer%20learning%20via%20local%20and%20global%20structure%20preservation&rft.jtitle=Signal,%20image%20and%20video%20processing&rft.au=Wang,%20Chao&rft.date=2019-06-01&rft.volume=13&rft.issue=4&rft.spage=753&rft.epage=760&rft.pages=753-760&rft.issn=1863-1703&rft.eissn=1863-1711&rft_id=info:doi/10.1007/s11760-018-1405-7&rft_dat=%3Cproquest_cross%3E2219656565%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=2219656565&rft_id=info:pmid/&rfr_iscdi=true |