Semantic segmentation method based on improved DenseNAS

Semantic segmentation method based on improved DenseNAS

The invention provides a semantic segmentation method based on improved DenseNAS. The semantic segmentation method comprises the following steps: (1) searching a proper deep neural network model by using the DenseNAS; (2) obtaining an optimal sub-network candidate based on a sub-network depth struct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WANG CHEN, MOMOKI AKIRA, HE LIXUAN, CHENG SHAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
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 WANG CHEN
MOMOKI AKIRA
HE LIXUAN
CHENG SHAN
description The invention provides a semantic segmentation method based on improved DenseNAS. The semantic segmentation method comprises the following steps: (1) searching a proper deep neural network model by using the DenseNAS; (2) obtaining an optimal sub-network candidate based on a sub-network depth structure selection algorithm, and selecting a shortest network and an optimal network from the candidate; and (3) taking the optimal network as a backbone network to obtain a teacher model FCN-long, taking the shortest network as a backbone network to obtain a student model FCN-short, extracting features of the image through the FCN-short obtained by knowledge distillation training, and obtaining a semantic segmentation image of the image. The invention provides a structure selection method based on sub-network depth, the precision of a selection network on a data set is improved, the advantages of a dense connection search space are exerted, and a semantic segmentation algorithm considering both efficiency and precisio
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115457269A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115457269A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115457269A3</originalsourceid><addsrcrecordid>eNrjZDAPTs1NzCvJTFYoTk3PTc0rSSzJzM9TyE0tychPUUhKLE5NUQDyM3MLivLLgGyX1LziVD_HYB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicmpdaEu_sZ2hoamJqbmRm6WhMjBoAygItxA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Semantic segmentation method based on improved DenseNAS</title><source>esp@cenet</source><creator>WANG CHEN ; MOMOKI AKIRA ; HE LIXUAN ; CHENG SHAN</creator><creatorcontrib>WANG CHEN ; MOMOKI AKIRA ; HE LIXUAN ; CHENG SHAN</creatorcontrib><description>The invention provides a semantic segmentation method based on improved DenseNAS. The semantic segmentation method comprises the following steps: (1) searching a proper deep neural network model by using the DenseNAS; (2) obtaining an optimal sub-network candidate based on a sub-network depth structure selection algorithm, and selecting a shortest network and an optimal network from the candidate; and (3) taking the optimal network as a backbone network to obtain a teacher model FCN-long, taking the shortest network as a backbone network to obtain a student model FCN-short, extracting features of the image through the FCN-short obtained by knowledge distillation training, and obtaining a semantic segmentation image of the image. The invention provides a structure selection method based on sub-network depth, the precision of a selection network on a data set is improved, the advantages of a dense connection search space are exerted, and a semantic segmentation algorithm considering both efficiency and precisio</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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&amp;date=20221209&amp;DB=EPODOC&amp;CC=CN&amp;NR=115457269A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20221209&amp;DB=EPODOC&amp;CC=CN&amp;NR=115457269A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG CHEN</creatorcontrib><creatorcontrib>MOMOKI AKIRA</creatorcontrib><creatorcontrib>HE LIXUAN</creatorcontrib><creatorcontrib>CHENG SHAN</creatorcontrib><title>Semantic segmentation method based on improved DenseNAS</title><description>The invention provides a semantic segmentation method based on improved DenseNAS. The semantic segmentation method comprises the following steps: (1) searching a proper deep neural network model by using the DenseNAS; (2) obtaining an optimal sub-network candidate based on a sub-network depth structure selection algorithm, and selecting a shortest network and an optimal network from the candidate; and (3) taking the optimal network as a backbone network to obtain a teacher model FCN-long, taking the shortest network as a backbone network to obtain a student model FCN-short, extracting features of the image through the FCN-short obtained by knowledge distillation training, and obtaining a semantic segmentation image of the image. The invention provides a structure selection method based on sub-network depth, the precision of a selection network on a data set is improved, the advantages of a dense connection search space are exerted, and a semantic segmentation algorithm considering both efficiency and precisio</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDAPTs1NzCvJTFYoTk3PTc0rSSzJzM9TyE0tychPUUhKLE5NUQDyM3MLivLLgGyX1LziVD_HYB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicmpdaEu_sZ2hoamJqbmRm6WhMjBoAygItxA</recordid><startdate>20221209</startdate><enddate>20221209</enddate><creator>WANG CHEN</creator><creator>MOMOKI AKIRA</creator><creator>HE LIXUAN</creator><creator>CHENG SHAN</creator><scope>EVB</scope></search><sort><creationdate>20221209</creationdate><title>Semantic segmentation method based on improved DenseNAS</title><author>WANG CHEN ; MOMOKI AKIRA ; HE LIXUAN ; CHENG SHAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115457269A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG CHEN</creatorcontrib><creatorcontrib>MOMOKI AKIRA</creatorcontrib><creatorcontrib>HE LIXUAN</creatorcontrib><creatorcontrib>CHENG SHAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG CHEN</au><au>MOMOKI AKIRA</au><au>HE LIXUAN</au><au>CHENG SHAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Semantic segmentation method based on improved DenseNAS</title><date>2022-12-09</date><risdate>2022</risdate><abstract>The invention provides a semantic segmentation method based on improved DenseNAS. The semantic segmentation method comprises the following steps: (1) searching a proper deep neural network model by using the DenseNAS; (2) obtaining an optimal sub-network candidate based on a sub-network depth structure selection algorithm, and selecting a shortest network and an optimal network from the candidate; and (3) taking the optimal network as a backbone network to obtain a teacher model FCN-long, taking the shortest network as a backbone network to obtain a student model FCN-short, extracting features of the image through the FCN-short obtained by knowledge distillation training, and obtaining a semantic segmentation image of the image. The invention provides a structure selection method based on sub-network depth, the precision of a selection network on a data set is improved, the advantages of a dense connection search space are exerted, and a semantic segmentation algorithm considering both efficiency and precisio</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115457269A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Semantic segmentation method based on improved DenseNAS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T06%3A13%3A22IST&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=WANG%20CHEN&rft.date=2022-12-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115457269A%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