Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-gr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-01
Hauptverfasser: Liu, Xiaofeng, Liu, Xiongchang, Hu, Bo, Ji, Wenxuan, Xing, Fangxu, Lu, Jun, You, Jane, C -C Jay Kuo, Georges El Fakhri, Woo, Jonghye
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Liu, Xiaofeng
Liu, Xiongchang
Hu, Bo
Ji, Wenxuan
Xing, Fangxu
Lu, Jun
You, Jane
C -C Jay Kuo
Georges El Fakhri
Woo, Jonghye
description Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases of with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on medical diagnosis tasks.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2475214895</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2475214895</sourcerecordid><originalsourceid>FETCH-proquest_journals_24752148953</originalsourceid><addsrcrecordid>eNqNyr0KwjAUQOEgCBbtOwScC21-bB3VKi5O6lyuNpWUmsTcRPHtdfABnM7wnRFJGOdFVgnGJiRF7PM8Z4uSSckTsj7GS3g7lcELvKJng9Ep_9SoWlrbO2hDVy24AEFbQzvr6UG1-goDrTXcjEWNMzLuYECV_jol8932tNlnzttHVBia3kZvvtQwUUpWiGop-X_XB95HOg8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2475214895</pqid></control><display><type>article</type><title>Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis</title><source>Freely Accessible Journals</source><creator>Liu, Xiaofeng ; Liu, Xiongchang ; Hu, Bo ; Ji, Wenxuan ; Xing, Fangxu ; Lu, Jun ; You, Jane ; C -C Jay Kuo ; Georges El Fakhri ; Woo, Jonghye</creator><creatorcontrib>Liu, Xiaofeng ; Liu, Xiongchang ; Hu, Bo ; Ji, Wenxuan ; Xing, Fangxu ; Lu, Jun ; You, Jane ; C -C Jay Kuo ; Georges El Fakhri ; Woo, Jonghye</creatorcontrib><description>Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases of with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on medical diagnosis tasks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptation ; Alignment ; Centroids ; Diagnosis ; Domains ; Medical diagnosis</subject><ispartof>arXiv.org, 2021-01</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>781,785</link.rule.ids></links><search><creatorcontrib>Liu, Xiaofeng</creatorcontrib><creatorcontrib>Liu, Xiongchang</creatorcontrib><creatorcontrib>Hu, Bo</creatorcontrib><creatorcontrib>Ji, Wenxuan</creatorcontrib><creatorcontrib>Xing, Fangxu</creatorcontrib><creatorcontrib>Lu, Jun</creatorcontrib><creatorcontrib>You, Jane</creatorcontrib><creatorcontrib>C -C Jay Kuo</creatorcontrib><creatorcontrib>Georges El Fakhri</creatorcontrib><creatorcontrib>Woo, Jonghye</creatorcontrib><title>Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis</title><title>arXiv.org</title><description>Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases of with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on medical diagnosis tasks.</description><subject>Adaptation</subject><subject>Alignment</subject><subject>Centroids</subject><subject>Diagnosis</subject><subject>Domains</subject><subject>Medical diagnosis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyr0KwjAUQOEgCBbtOwScC21-bB3VKi5O6lyuNpWUmsTcRPHtdfABnM7wnRFJGOdFVgnGJiRF7PM8Z4uSSckTsj7GS3g7lcELvKJng9Ep_9SoWlrbO2hDVy24AEFbQzvr6UG1-goDrTXcjEWNMzLuYECV_jol8932tNlnzttHVBia3kZvvtQwUUpWiGop-X_XB95HOg8</recordid><startdate>20210111</startdate><enddate>20210111</enddate><creator>Liu, Xiaofeng</creator><creator>Liu, Xiongchang</creator><creator>Hu, Bo</creator><creator>Ji, Wenxuan</creator><creator>Xing, Fangxu</creator><creator>Lu, Jun</creator><creator>You, Jane</creator><creator>C -C Jay Kuo</creator><creator>Georges El Fakhri</creator><creator>Woo, Jonghye</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210111</creationdate><title>Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis</title><author>Liu, Xiaofeng ; Liu, Xiongchang ; Hu, Bo ; Ji, Wenxuan ; Xing, Fangxu ; Lu, Jun ; You, Jane ; C -C Jay Kuo ; Georges El Fakhri ; Woo, Jonghye</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24752148953</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adaptation</topic><topic>Alignment</topic><topic>Centroids</topic><topic>Diagnosis</topic><topic>Domains</topic><topic>Medical diagnosis</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Xiaofeng</creatorcontrib><creatorcontrib>Liu, Xiongchang</creatorcontrib><creatorcontrib>Hu, Bo</creatorcontrib><creatorcontrib>Ji, Wenxuan</creatorcontrib><creatorcontrib>Xing, Fangxu</creatorcontrib><creatorcontrib>Lu, Jun</creatorcontrib><creatorcontrib>You, Jane</creatorcontrib><creatorcontrib>C -C Jay Kuo</creatorcontrib><creatorcontrib>Georges El Fakhri</creatorcontrib><creatorcontrib>Woo, Jonghye</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Xiaofeng</au><au>Liu, Xiongchang</au><au>Hu, Bo</au><au>Ji, Wenxuan</au><au>Xing, Fangxu</au><au>Lu, Jun</au><au>You, Jane</au><au>C -C Jay Kuo</au><au>Georges El Fakhri</au><au>Woo, Jonghye</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis</atitle><jtitle>arXiv.org</jtitle><date>2021-01-11</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases of with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on medical diagnosis tasks.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-01
issn 2331-8422
language eng
recordid cdi_proquest_journals_2475214895
source Freely Accessible Journals
subjects Adaptation
Alignment
Centroids
Diagnosis
Domains
Medical diagnosis
title Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T18%3A12%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Subtype-aware%20Unsupervised%20Domain%20Adaptation%20for%20Medical%20Diagnosis&rft.jtitle=arXiv.org&rft.au=Liu,%20Xiaofeng&rft.date=2021-01-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2475214895%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2475214895&rft_id=info:pmid/&rfr_iscdi=true