TRAINING IMAGE SIGNAL PROCESSORS USING INTERMEDIATE LOSS FUNCTIONS
In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a co...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| 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 | Zivkovic, Zoran Sutic, Aleksandar Michael, Gilad |
| description | In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy of the computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2019050682A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2019050682A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2019050682A13</originalsourceid><addsrcrecordid>eNrjZHAKCXL09PP0c1fw9HV0d1UI9nT3c_RRCAjyd3YNDvYPClYIDQbL-oW4Bvm6ung6hrgq-PgHByu4hfo5h3j6-wXzMLCmJeYUp_JCaW4GZTfXEGcP3dSC_PjU4oLE5NS81JL40GAjA0NLA1MDMwsjR0Nj4lQBANoKLIo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>TRAINING IMAGE SIGNAL PROCESSORS USING INTERMEDIATE LOSS FUNCTIONS</title><source>esp@cenet</source><creator>Zivkovic, Zoran ; Sutic, Aleksandar ; Michael, Gilad</creator><creatorcontrib>Zivkovic, Zoran ; Sutic, Aleksandar ; Michael, Gilad</creatorcontrib><description>In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy of the computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2019</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=20190214&DB=EPODOC&CC=US&NR=2019050682A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25566,76549</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190214&DB=EPODOC&CC=US&NR=2019050682A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Zivkovic, Zoran</creatorcontrib><creatorcontrib>Sutic, Aleksandar</creatorcontrib><creatorcontrib>Michael, Gilad</creatorcontrib><title>TRAINING IMAGE SIGNAL PROCESSORS USING INTERMEDIATE LOSS FUNCTIONS</title><description>In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy of the computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHAKCXL09PP0c1fw9HV0d1UI9nT3c_RRCAjyd3YNDvYPClYIDQbL-oW4Bvm6ung6hrgq-PgHByu4hfo5h3j6-wXzMLCmJeYUp_JCaW4GZTfXEGcP3dSC_PjU4oLE5NS81JL40GAjA0NLA1MDMwsjR0Nj4lQBANoKLIo</recordid><startdate>20190214</startdate><enddate>20190214</enddate><creator>Zivkovic, Zoran</creator><creator>Sutic, Aleksandar</creator><creator>Michael, Gilad</creator><scope>EVB</scope></search><sort><creationdate>20190214</creationdate><title>TRAINING IMAGE SIGNAL PROCESSORS USING INTERMEDIATE LOSS FUNCTIONS</title><author>Zivkovic, Zoran ; Sutic, Aleksandar ; Michael, Gilad</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2019050682A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>Zivkovic, Zoran</creatorcontrib><creatorcontrib>Sutic, Aleksandar</creatorcontrib><creatorcontrib>Michael, Gilad</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zivkovic, Zoran</au><au>Sutic, Aleksandar</au><au>Michael, Gilad</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>TRAINING IMAGE SIGNAL PROCESSORS USING INTERMEDIATE LOSS FUNCTIONS</title><date>2019-02-14</date><risdate>2019</risdate><abstract>In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy of the computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2019050682A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | TRAINING IMAGE SIGNAL PROCESSORS USING INTERMEDIATE LOSS FUNCTIONS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T02%3A35%3A24IST&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=Zivkovic,%20Zoran&rft.date=2019-02-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2019050682A1%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 |