Semantic Attribute Matching Networks
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming their limitations. SAM-Net accomplishes this through an itera...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Kim, Seungryong Min, Dongbo Jeong, Somi Kim, Sunok Jeon, Sangryul Sohn, Kwanghoon |
| description | We present semantic attribute matching networks (SAM-Net) for jointly
establishing correspondences and transferring attributes across semantically
similar images, which intelligently weaves the advantages of the two tasks
while overcoming their limitations. SAM-Net accomplishes this through an
iterative process of establishing reliable correspondences by reducing the
attribute discrepancy between the images and synthesizing attribute transferred
images using the learned correspondences. To learn the networks using weak
supervisions in the form of image pairs, we present a semantic attribute
matching loss based on the matching similarity between an attribute transferred
source feature and a warped target feature. With SAM-Net, the state-of-the-art
performance is attained on several benchmarks for semantic matching and
attribute transfer. |
| doi_str_mv | 10.48550/arxiv.1904.02969 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1904_02969</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1904_02969</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-2e31b8f7a968bc754cf9defc875f757c5a46058966a1468bac4abc1268448ec23</originalsourceid><addsrcrecordid>eNotzj1vwjAUhWEvDBXlB3QiA2uCnVx_jQi1pRJtB9ij64sNVklaGUPh39PSTmd5dfQw9iB4BUZKPsV0jqdKWA4Vr62yd2yy8h32OVIxyzlFd8y-eMVMu9hvizefvz_Tx-GeDQLuD370v0O2fnpczxfl8v35ZT5blqi0LWvfCGeCRquMIy2Bgt34QEbLoKUmiaC4NFYpFPCTIAE6ErUyAMZT3QzZ-O_2xmy_UuwwXdpfbnvjNlfoMzmy</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Semantic Attribute Matching Networks</title><source>arXiv.org</source><creator>Kim, Seungryong ; Min, Dongbo ; Jeong, Somi ; Kim, Sunok ; Jeon, Sangryul ; Sohn, Kwanghoon</creator><creatorcontrib>Kim, Seungryong ; Min, Dongbo ; Jeong, Somi ; Kim, Sunok ; Jeon, Sangryul ; Sohn, Kwanghoon</creatorcontrib><description>We present semantic attribute matching networks (SAM-Net) for jointly
establishing correspondences and transferring attributes across semantically
similar images, which intelligently weaves the advantages of the two tasks
while overcoming their limitations. SAM-Net accomplishes this through an
iterative process of establishing reliable correspondences by reducing the
attribute discrepancy between the images and synthesizing attribute transferred
images using the learned correspondences. To learn the networks using weak
supervisions in the form of image pairs, we present a semantic attribute
matching loss based on the matching similarity between an attribute transferred
source feature and a warped target feature. With SAM-Net, the state-of-the-art
performance is attained on several benchmarks for semantic matching and
attribute transfer.</description><identifier>DOI: 10.48550/arxiv.1904.02969</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2019-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1904.02969$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1904.02969$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kim, Seungryong</creatorcontrib><creatorcontrib>Min, Dongbo</creatorcontrib><creatorcontrib>Jeong, Somi</creatorcontrib><creatorcontrib>Kim, Sunok</creatorcontrib><creatorcontrib>Jeon, Sangryul</creatorcontrib><creatorcontrib>Sohn, Kwanghoon</creatorcontrib><title>Semantic Attribute Matching Networks</title><description>We present semantic attribute matching networks (SAM-Net) for jointly
establishing correspondences and transferring attributes across semantically
similar images, which intelligently weaves the advantages of the two tasks
while overcoming their limitations. SAM-Net accomplishes this through an
iterative process of establishing reliable correspondences by reducing the
attribute discrepancy between the images and synthesizing attribute transferred
images using the learned correspondences. To learn the networks using weak
supervisions in the form of image pairs, we present a semantic attribute
matching loss based on the matching similarity between an attribute transferred
source feature and a warped target feature. With SAM-Net, the state-of-the-art
performance is attained on several benchmarks for semantic matching and
attribute transfer.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzj1vwjAUhWEvDBXlB3QiA2uCnVx_jQi1pRJtB9ij64sNVklaGUPh39PSTmd5dfQw9iB4BUZKPsV0jqdKWA4Vr62yd2yy8h32OVIxyzlFd8y-eMVMu9hvizefvz_Tx-GeDQLuD370v0O2fnpczxfl8v35ZT5blqi0LWvfCGeCRquMIy2Bgt34QEbLoKUmiaC4NFYpFPCTIAE6ErUyAMZT3QzZ-O_2xmy_UuwwXdpfbnvjNlfoMzmy</recordid><startdate>20190405</startdate><enddate>20190405</enddate><creator>Kim, Seungryong</creator><creator>Min, Dongbo</creator><creator>Jeong, Somi</creator><creator>Kim, Sunok</creator><creator>Jeon, Sangryul</creator><creator>Sohn, Kwanghoon</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190405</creationdate><title>Semantic Attribute Matching Networks</title><author>Kim, Seungryong ; Min, Dongbo ; Jeong, Somi ; Kim, Sunok ; Jeon, Sangryul ; Sohn, Kwanghoon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-2e31b8f7a968bc754cf9defc875f757c5a46058966a1468bac4abc1268448ec23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Kim, Seungryong</creatorcontrib><creatorcontrib>Min, Dongbo</creatorcontrib><creatorcontrib>Jeong, Somi</creatorcontrib><creatorcontrib>Kim, Sunok</creatorcontrib><creatorcontrib>Jeon, Sangryul</creatorcontrib><creatorcontrib>Sohn, Kwanghoon</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kim, Seungryong</au><au>Min, Dongbo</au><au>Jeong, Somi</au><au>Kim, Sunok</au><au>Jeon, Sangryul</au><au>Sohn, Kwanghoon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Semantic Attribute Matching Networks</atitle><date>2019-04-05</date><risdate>2019</risdate><abstract>We present semantic attribute matching networks (SAM-Net) for jointly
establishing correspondences and transferring attributes across semantically
similar images, which intelligently weaves the advantages of the two tasks
while overcoming their limitations. SAM-Net accomplishes this through an
iterative process of establishing reliable correspondences by reducing the
attribute discrepancy between the images and synthesizing attribute transferred
images using the learned correspondences. To learn the networks using weak
supervisions in the form of image pairs, we present a semantic attribute
matching loss based on the matching similarity between an attribute transferred
source feature and a warped target feature. With SAM-Net, the state-of-the-art
performance is attained on several benchmarks for semantic matching and
attribute transfer.</abstract><doi>10.48550/arxiv.1904.02969</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1904.02969 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1904_02969 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition |
| title | Semantic Attribute Matching Networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-15T19%3A47%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Semantic%20Attribute%20Matching%20Networks&rft.au=Kim,%20Seungryong&rft.date=2019-04-05&rft_id=info:doi/10.48550/arxiv.1904.02969&rft_dat=%3Carxiv_GOX%3E1904_02969%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |