Model training method, device and equipment based on data augmentation
The embodiment of the invention discloses a model training method, device and equipment based on data augmentation. The method comprises the steps that a set of training samples is obtained, and the set comprises labeled samples and unlabeled samples; encoding to generate a first hidden variable cor...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | FANG JUNPENG TANG CAIZHI |
| description | The embodiment of the invention discloses a model training method, device and equipment based on data augmentation. The method comprises the steps that a set of training samples is obtained, and the set comprises labeled samples and unlabeled samples; encoding to generate a first hidden variable corresponding to the labeled sample, and encoding to generate a second hidden variable corresponding to the unlabeled sample; generating a first classification result according to the first hidden variable, and determining a supervision loss value of the first classification result and the marked sample; decoding the second hidden variable to generate augmented data, and encoding the augmented data to generate a third hidden variable; generating a second classification result according to the second hidden variable, generating a third classification result according to the third hidden variable, and determining a consistency loss value of the second classification result and the third classification result; and fusing |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115964633A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115964633A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115964633A3</originalsourceid><addsrcrecordid>eNqNyjEKwkAQRuFtLES9w9hrEVYDlhIMNlrZhzHzmywks6s78fwieACrBx9v7upLFAxkLw4atKMR1kfZkOAdWhCrEJ5TSCPU6M4ZQlFJ2Jh46r7KFqIu3ezBQ8bq14Vb16dbdd4ixQY5cQuFNdW1KPaHcld6f_T_PB8C1jNQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Model training method, device and equipment based on data augmentation</title><source>esp@cenet</source><creator>FANG JUNPENG ; TANG CAIZHI</creator><creatorcontrib>FANG JUNPENG ; TANG CAIZHI</creatorcontrib><description>The embodiment of the invention discloses a model training method, device and equipment based on data augmentation. The method comprises the steps that a set of training samples is obtained, and the set comprises labeled samples and unlabeled samples; encoding to generate a first hidden variable corresponding to the labeled sample, and encoding to generate a second hidden variable corresponding to the unlabeled sample; generating a first classification result according to the first hidden variable, and determining a supervision loss value of the first classification result and the marked sample; decoding the second hidden variable to generate augmented data, and encoding the augmented data to generate a third hidden variable; generating a second classification result according to the second hidden variable, generating a third classification result according to the third hidden variable, and determining a consistency loss value of the second classification result and the third classification result; and fusing</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230414&DB=EPODOC&CC=CN&NR=115964633A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25555,76308</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230414&DB=EPODOC&CC=CN&NR=115964633A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FANG JUNPENG</creatorcontrib><creatorcontrib>TANG CAIZHI</creatorcontrib><title>Model training method, device and equipment based on data augmentation</title><description>The embodiment of the invention discloses a model training method, device and equipment based on data augmentation. The method comprises the steps that a set of training samples is obtained, and the set comprises labeled samples and unlabeled samples; encoding to generate a first hidden variable corresponding to the labeled sample, and encoding to generate a second hidden variable corresponding to the unlabeled sample; generating a first classification result according to the first hidden variable, and determining a supervision loss value of the first classification result and the marked sample; decoding the second hidden variable to generate augmented data, and encoding the augmented data to generate a third hidden variable; generating a second classification result according to the second hidden variable, generating a third classification result according to the third hidden variable, and determining a consistency loss value of the second classification result and the third classification result; and fusing</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEKwkAQRuFtLES9w9hrEVYDlhIMNlrZhzHzmywks6s78fwieACrBx9v7upLFAxkLw4atKMR1kfZkOAdWhCrEJ5TSCPU6M4ZQlFJ2Jh46r7KFqIu3ezBQ8bq14Vb16dbdd4ixQY5cQuFNdW1KPaHcld6f_T_PB8C1jNQ</recordid><startdate>20230414</startdate><enddate>20230414</enddate><creator>FANG JUNPENG</creator><creator>TANG CAIZHI</creator><scope>EVB</scope></search><sort><creationdate>20230414</creationdate><title>Model training method, device and equipment based on data augmentation</title><author>FANG JUNPENG ; TANG CAIZHI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115964633A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>FANG JUNPENG</creatorcontrib><creatorcontrib>TANG CAIZHI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FANG JUNPENG</au><au>TANG CAIZHI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Model training method, device and equipment based on data augmentation</title><date>2023-04-14</date><risdate>2023</risdate><abstract>The embodiment of the invention discloses a model training method, device and equipment based on data augmentation. The method comprises the steps that a set of training samples is obtained, and the set comprises labeled samples and unlabeled samples; encoding to generate a first hidden variable corresponding to the labeled sample, and encoding to generate a second hidden variable corresponding to the unlabeled sample; generating a first classification result according to the first hidden variable, and determining a supervision loss value of the first classification result and the marked sample; decoding the second hidden variable to generate augmented data, and encoding the augmented data to generate a third hidden variable; generating a second classification result according to the second hidden variable, generating a third classification result according to the third hidden variable, and determining a consistency loss value of the second classification result and the third classification result; and fusing</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115964633A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Model training method, device and equipment based on data augmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T01%3A26%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=FANG%20JUNPENG&rft.date=2023-04-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115964633A%3C/epo_EVB%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 |