HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS

This application discloses a header model for instance segmentation, an instance segmentation model, an image segmentation method and apparatus, and relates to the field of artificial intelligence technologies such as computer vision and deep learning technologies. The header model includes: a targe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: FENG, Yuan, XIN, Ying, ZHENG, Honghui, WANG, Xiaodi, YUAN, Pengcheng, ZHANG, Bin, PENG, Yan, HAN, Shumin, LONG, Xiang, LIN, Shufei
Format: Patent
Sprache:eng ; fre ; ger
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 FENG, Yuan
XIN, Ying
ZHENG, Honghui
WANG, Xiaodi
YUAN, Pengcheng
ZHANG, Bin
PENG, Yan
HAN, Shumin
LONG, Xiang
LIN, Shufei
description This application discloses a header model for instance segmentation, an instance segmentation model, an image segmentation method and apparatus, and relates to the field of artificial intelligence technologies such as computer vision and deep learning technologies. The header model includes: a target box branch, including a first branch and a second branch, where the first branch is configured to process an inputted first feature map to obtain class information and confidence of a target box, and the second branch is configured to process the first feature map to obtain location information of the target box; a mask branch, configured to process an inputted second feature map to obtain mask information; the second feature map is a feature map outputted by an ROI extraction module, and the first feature map is a feature map resulting from a pooling performed on the second feature map. The application makes the segmentation information and confidence predicted by the header more accurate, resulting in a finer segmentation result of the instance segmentation.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3872704A2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3872704A2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3872704A23</originalsourceid><addsrcrecordid>eNrjZMjxcHV0cQ1S8PV3cfVRcPMPUvD0Cw5x9HN2VQh2dfd19QtxDPH099PBLgzRBpT0dXRHl3EN8fB3UXD0A-KAAMcgx5DQYB4G1rTEnOJUXijNzaDg5hri7KGbWpAfn1pckJicmpdaEu8aYGxhbmRuYOJoZEyEEgB67DZB</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS</title><source>esp@cenet</source><creator>FENG, Yuan ; XIN, Ying ; ZHENG, Honghui ; WANG, Xiaodi ; YUAN, Pengcheng ; ZHANG, Bin ; PENG, Yan ; HAN, Shumin ; LONG, Xiang ; LIN, Shufei</creator><creatorcontrib>FENG, Yuan ; XIN, Ying ; ZHENG, Honghui ; WANG, Xiaodi ; YUAN, Pengcheng ; ZHANG, Bin ; PENG, Yan ; HAN, Shumin ; LONG, Xiang ; LIN, Shufei</creatorcontrib><description>This application discloses a header model for instance segmentation, an instance segmentation model, an image segmentation method and apparatus, and relates to the field of artificial intelligence technologies such as computer vision and deep learning technologies. The header model includes: a target box branch, including a first branch and a second branch, where the first branch is configured to process an inputted first feature map to obtain class information and confidence of a target box, and the second branch is configured to process the first feature map to obtain location information of the target box; a mask branch, configured to process an inputted second feature map to obtain mask information; the second feature map is a feature map outputted by an ROI extraction module, and the first feature map is a feature map resulting from a pooling performed on the second feature map. The application makes the segmentation information and confidence predicted by the header more accurate, resulting in a finer segmentation result of the instance segmentation.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2021</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=20210901&amp;DB=EPODOC&amp;CC=EP&amp;NR=3872704A2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210901&amp;DB=EPODOC&amp;CC=EP&amp;NR=3872704A2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FENG, Yuan</creatorcontrib><creatorcontrib>XIN, Ying</creatorcontrib><creatorcontrib>ZHENG, Honghui</creatorcontrib><creatorcontrib>WANG, Xiaodi</creatorcontrib><creatorcontrib>YUAN, Pengcheng</creatorcontrib><creatorcontrib>ZHANG, Bin</creatorcontrib><creatorcontrib>PENG, Yan</creatorcontrib><creatorcontrib>HAN, Shumin</creatorcontrib><creatorcontrib>LONG, Xiang</creatorcontrib><creatorcontrib>LIN, Shufei</creatorcontrib><title>HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS</title><description>This application discloses a header model for instance segmentation, an instance segmentation model, an image segmentation method and apparatus, and relates to the field of artificial intelligence technologies such as computer vision and deep learning technologies. The header model includes: a target box branch, including a first branch and a second branch, where the first branch is configured to process an inputted first feature map to obtain class information and confidence of a target box, and the second branch is configured to process the first feature map to obtain location information of the target box; a mask branch, configured to process an inputted second feature map to obtain mask information; the second feature map is a feature map outputted by an ROI extraction module, and the first feature map is a feature map resulting from a pooling performed on the second feature map. The application makes the segmentation information and confidence predicted by the header more accurate, resulting in a finer segmentation result of the instance segmentation.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZMjxcHV0cQ1S8PV3cfVRcPMPUvD0Cw5x9HN2VQh2dfd19QtxDPH099PBLgzRBpT0dXRHl3EN8fB3UXD0A-KAAMcgx5DQYB4G1rTEnOJUXijNzaDg5hri7KGbWpAfn1pckJicmpdaEu8aYGxhbmRuYOJoZEyEEgB67DZB</recordid><startdate>20210901</startdate><enddate>20210901</enddate><creator>FENG, Yuan</creator><creator>XIN, Ying</creator><creator>ZHENG, Honghui</creator><creator>WANG, Xiaodi</creator><creator>YUAN, Pengcheng</creator><creator>ZHANG, Bin</creator><creator>PENG, Yan</creator><creator>HAN, Shumin</creator><creator>LONG, Xiang</creator><creator>LIN, Shufei</creator><scope>EVB</scope></search><sort><creationdate>20210901</creationdate><title>HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS</title><author>FENG, Yuan ; XIN, Ying ; ZHENG, Honghui ; WANG, Xiaodi ; YUAN, Pengcheng ; ZHANG, Bin ; PENG, Yan ; HAN, Shumin ; LONG, Xiang ; LIN, Shufei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3872704A23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>FENG, Yuan</creatorcontrib><creatorcontrib>XIN, Ying</creatorcontrib><creatorcontrib>ZHENG, Honghui</creatorcontrib><creatorcontrib>WANG, Xiaodi</creatorcontrib><creatorcontrib>YUAN, Pengcheng</creatorcontrib><creatorcontrib>ZHANG, Bin</creatorcontrib><creatorcontrib>PENG, Yan</creatorcontrib><creatorcontrib>HAN, Shumin</creatorcontrib><creatorcontrib>LONG, Xiang</creatorcontrib><creatorcontrib>LIN, Shufei</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FENG, Yuan</au><au>XIN, Ying</au><au>ZHENG, Honghui</au><au>WANG, Xiaodi</au><au>YUAN, Pengcheng</au><au>ZHANG, Bin</au><au>PENG, Yan</au><au>HAN, Shumin</au><au>LONG, Xiang</au><au>LIN, Shufei</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS</title><date>2021-09-01</date><risdate>2021</risdate><abstract>This application discloses a header model for instance segmentation, an instance segmentation model, an image segmentation method and apparatus, and relates to the field of artificial intelligence technologies such as computer vision and deep learning technologies. The header model includes: a target box branch, including a first branch and a second branch, where the first branch is configured to process an inputted first feature map to obtain class information and confidence of a target box, and the second branch is configured to process the first feature map to obtain location information of the target box; a mask branch, configured to process an inputted second feature map to obtain mask information; the second feature map is a feature map outputted by an ROI extraction module, and the first feature map is a feature map resulting from a pooling performed on the second feature map. The application makes the segmentation information and confidence predicted by the header more accurate, resulting in a finer segmentation result of the instance segmentation.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP3872704A2
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A16%3A38IST&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=FENG,%20Yuan&rft.date=2021-09-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3872704A2%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