Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation
Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remarkable results recently in terms of predicting ability, which implies the effecti...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2023-03 |
---|---|
Hauptverfasser: | , , |
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 | Xiao, Wenxiao Ding, Zhengming Liu, Hongfu |
description | Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remarkable results recently in terms of predicting ability, which implies the effectiveness of the aforementioned knowledge transferring. However, state-of-the-art methods rarely probe deeper into the transferred mechanism, leaving the true essence of such knowledge obscure. Recognizing its importance in the adaptation process, we propose an interpretive model of unsupervised domain adaptation, as the first attempt to visually unveil the mystery of transferred knowledge. Adapting the existing concept of the prototype from visual image interpretation to the DA task, our model similarly extracts shared information from the domain-invariant representations as prototype vectors. Furthermore, we extend the current prototype method with our novel prediction calibration and knowledge fidelity preservation modules, to orientate the learned prototypes to the actual transferred knowledge. By visualizing these prototypes, our method not only provides an intuitive explanation for the base model's predictions but also unveils transfer knowledge by matching the image patches with the same semantics across both source and target domains. Comprehensive experiments and in-depth explorations demonstrate the efficacy of our method in understanding the transferred mechanism and its potential in downstream tasks including model diagnosis. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2784121860</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2784121860</sourcerecordid><originalsourceid>FETCH-proquest_journals_27841218603</originalsourceid><addsrcrecordid>eNqNi7sKwjAUQIMgWLT_EHAutElfuBUfKOKmDi4lkNuSUm9qHhX8ejv4AU5nOOfMSMA4T6IyZWxBQmu7OI5ZXrAs4wF53JX1olcfhS29GoG2AWNA0jPqdw-yhQ2tkJ7QgRkMODUCvWgJPdUNvaH1A5hR2WnY6adQSCspBiec0rgi80b0FsIfl2R92F-3x2gw-uXBurrT3uCkalaUacKSMo_5f9UXdPlDHA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2784121860</pqid></control><display><type>article</type><title>Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation</title><source>Free E- Journals</source><creator>Xiao, Wenxiao ; Ding, Zhengming ; Liu, Hongfu</creator><creatorcontrib>Xiao, Wenxiao ; Ding, Zhengming ; Liu, Hongfu</creatorcontrib><description>Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remarkable results recently in terms of predicting ability, which implies the effectiveness of the aforementioned knowledge transferring. However, state-of-the-art methods rarely probe deeper into the transferred mechanism, leaving the true essence of such knowledge obscure. Recognizing its importance in the adaptation process, we propose an interpretive model of unsupervised domain adaptation, as the first attempt to visually unveil the mystery of transferred knowledge. Adapting the existing concept of the prototype from visual image interpretation to the DA task, our model similarly extracts shared information from the domain-invariant representations as prototype vectors. Furthermore, we extend the current prototype method with our novel prediction calibration and knowledge fidelity preservation modules, to orientate the learned prototypes to the actual transferred knowledge. By visualizing these prototypes, our method not only provides an intuitive explanation for the base model's predictions but also unveils transfer knowledge by matching the image patches with the same semantics across both source and target domains. Comprehensive experiments and in-depth explorations demonstrate the efficacy of our method in understanding the transferred mechanism and its potential in downstream tasks including model diagnosis.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptation ; Domains ; Knowledge ; Knowledge management ; Prototypes ; Semantics</subject><ispartof>arXiv.org, 2023-03</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (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>780,784</link.rule.ids></links><search><creatorcontrib>Xiao, Wenxiao</creatorcontrib><creatorcontrib>Ding, Zhengming</creatorcontrib><creatorcontrib>Liu, Hongfu</creatorcontrib><title>Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation</title><title>arXiv.org</title><description>Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remarkable results recently in terms of predicting ability, which implies the effectiveness of the aforementioned knowledge transferring. However, state-of-the-art methods rarely probe deeper into the transferred mechanism, leaving the true essence of such knowledge obscure. Recognizing its importance in the adaptation process, we propose an interpretive model of unsupervised domain adaptation, as the first attempt to visually unveil the mystery of transferred knowledge. Adapting the existing concept of the prototype from visual image interpretation to the DA task, our model similarly extracts shared information from the domain-invariant representations as prototype vectors. Furthermore, we extend the current prototype method with our novel prediction calibration and knowledge fidelity preservation modules, to orientate the learned prototypes to the actual transferred knowledge. By visualizing these prototypes, our method not only provides an intuitive explanation for the base model's predictions but also unveils transfer knowledge by matching the image patches with the same semantics across both source and target domains. Comprehensive experiments and in-depth explorations demonstrate the efficacy of our method in understanding the transferred mechanism and its potential in downstream tasks including model diagnosis.</description><subject>Adaptation</subject><subject>Domains</subject><subject>Knowledge</subject><subject>Knowledge management</subject><subject>Prototypes</subject><subject>Semantics</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi7sKwjAUQIMgWLT_EHAutElfuBUfKOKmDi4lkNuSUm9qHhX8ejv4AU5nOOfMSMA4T6IyZWxBQmu7OI5ZXrAs4wF53JX1olcfhS29GoG2AWNA0jPqdw-yhQ2tkJ7QgRkMODUCvWgJPdUNvaH1A5hR2WnY6adQSCspBiec0rgi80b0FsIfl2R92F-3x2gw-uXBurrT3uCkalaUacKSMo_5f9UXdPlDHA</recordid><startdate>20230304</startdate><enddate>20230304</enddate><creator>Xiao, Wenxiao</creator><creator>Ding, Zhengming</creator><creator>Liu, Hongfu</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>20230304</creationdate><title>Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation</title><author>Xiao, Wenxiao ; Ding, Zhengming ; Liu, Hongfu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27841218603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Adaptation</topic><topic>Domains</topic><topic>Knowledge</topic><topic>Knowledge management</topic><topic>Prototypes</topic><topic>Semantics</topic><toplevel>online_resources</toplevel><creatorcontrib>Xiao, Wenxiao</creatorcontrib><creatorcontrib>Ding, Zhengming</creatorcontrib><creatorcontrib>Liu, Hongfu</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Publicly Available Content Database</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>Xiao, Wenxiao</au><au>Ding, Zhengming</au><au>Liu, Hongfu</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation</atitle><jtitle>arXiv.org</jtitle><date>2023-03-04</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remarkable results recently in terms of predicting ability, which implies the effectiveness of the aforementioned knowledge transferring. However, state-of-the-art methods rarely probe deeper into the transferred mechanism, leaving the true essence of such knowledge obscure. Recognizing its importance in the adaptation process, we propose an interpretive model of unsupervised domain adaptation, as the first attempt to visually unveil the mystery of transferred knowledge. Adapting the existing concept of the prototype from visual image interpretation to the DA task, our model similarly extracts shared information from the domain-invariant representations as prototype vectors. Furthermore, we extend the current prototype method with our novel prediction calibration and knowledge fidelity preservation modules, to orientate the learned prototypes to the actual transferred knowledge. By visualizing these prototypes, our method not only provides an intuitive explanation for the base model's predictions but also unveils transfer knowledge by matching the image patches with the same semantics across both source and target domains. Comprehensive experiments and in-depth explorations demonstrate the efficacy of our method in understanding the transferred mechanism and its potential in downstream tasks including model diagnosis.</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, 2023-03 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2784121860 |
source | Free E- Journals |
subjects | Adaptation Domains Knowledge Knowledge management Prototypes Semantics |
title | Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T21%3A31%3A09IST&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=Visualizing%20Transferred%20Knowledge:%20An%20Interpretive%20Model%20of%20Unsupervised%20Domain%20Adaptation&rft.jtitle=arXiv.org&rft.au=Xiao,%20Wenxiao&rft.date=2023-03-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2784121860%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2784121860&rft_id=info:pmid/&rfr_iscdi=true |