Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach

Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels ar...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-06
Hauptverfasser: Mengcheng Lan, Meng, Min, Yu, Jun, Wu, Jigang
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 Mengcheng Lan
Meng, Min
Yu, Jun
Wu, Jigang
description Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels are easy to collect, stimulating a great demand for automatic recognition in a generalized setting, i.e., weakly-supervised partial domain adaptation (WS-PDA), which transfers a classifier from a large source domain with noises in labels to a small unlabeled target domain. As such, the key issues of WS-PDA are: 1) how to sufficiently discover the knowledge from the noisy labeled source domain and the unlabeled target domain, and 2) how to successfully adapt the knowledge across domains. In this paper, we propose a simple yet effective domain adaptation approach, termed as self-paced transfer classifier learning (SP-TCL), to address the above issues, which could be regarded as a well-performing baseline for several generalized domain adaptation tasks. The proposed model is established upon the self-paced learning scheme, seeking a preferable classifier for the target domain. Specifically, SP-TCL learns to discover faithful knowledge via a carefully designed prudent loss function and simultaneously adapts the learned knowledge to the target domain by iteratively excluding source examples from training under the self-paced fashion. Extensive evaluations on several benchmark datasets demonstrate that SP-TCL significantly outperforms state-of-the-art approaches on several generalized domain adaptation tasks.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3070856780</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3070856780</sourcerecordid><originalsourceid>FETCH-proquest_journals_30708567803</originalsourceid><addsrcrecordid>eNqNiksKwjAUAIMgWLR3CLguxMR-cFesIuhCUHRZHu2zptakJmnF29uFB3A1AzMj4nEhFkGy5HxCfGtrxhiPYh6GwiOXA4JRUlXUaZpJW-geDd0r_W6wrHBFU3pFeDSf4NS1aHppsaRHME5CQzP9BKloWkLrwEk9aNsaDcV9RsY3aCz6P07JfLs5r3fBkF8dWpfXujNqSLlgMUvCKE6Y-O_6AtR7QNw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3070856780</pqid></control><display><type>article</type><title>Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach</title><source>Free E- Journals</source><creator>Mengcheng Lan ; Meng, Min ; Yu, Jun ; Wu, Jigang</creator><creatorcontrib>Mengcheng Lan ; Meng, Min ; Yu, Jun ; Wu, Jigang</creatorcontrib><description>Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels are easy to collect, stimulating a great demand for automatic recognition in a generalized setting, i.e., weakly-supervised partial domain adaptation (WS-PDA), which transfers a classifier from a large source domain with noises in labels to a small unlabeled target domain. As such, the key issues of WS-PDA are: 1) how to sufficiently discover the knowledge from the noisy labeled source domain and the unlabeled target domain, and 2) how to successfully adapt the knowledge across domains. In this paper, we propose a simple yet effective domain adaptation approach, termed as self-paced transfer classifier learning (SP-TCL), to address the above issues, which could be regarded as a well-performing baseline for several generalized domain adaptation tasks. The proposed model is established upon the self-paced learning scheme, seeking a preferable classifier for the target domain. Specifically, SP-TCL learns to discover faithful knowledge via a carefully designed prudent loss function and simultaneously adapts the learned knowledge to the target domain by iteratively excluding source examples from training under the self-paced fashion. Extensive evaluations on several benchmark datasets demonstrate that SP-TCL significantly outperforms state-of-the-art approaches on several generalized domain adaptation tasks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptation ; Annotations ; Classifiers ; Datasets ; Knowledge ; Labels ; Learning</subject><ispartof>arXiv.org, 2024-06</ispartof><rights>2024. 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>Mengcheng Lan</creatorcontrib><creatorcontrib>Meng, Min</creatorcontrib><creatorcontrib>Yu, Jun</creatorcontrib><creatorcontrib>Wu, Jigang</creatorcontrib><title>Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach</title><title>arXiv.org</title><description>Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels are easy to collect, stimulating a great demand for automatic recognition in a generalized setting, i.e., weakly-supervised partial domain adaptation (WS-PDA), which transfers a classifier from a large source domain with noises in labels to a small unlabeled target domain. As such, the key issues of WS-PDA are: 1) how to sufficiently discover the knowledge from the noisy labeled source domain and the unlabeled target domain, and 2) how to successfully adapt the knowledge across domains. In this paper, we propose a simple yet effective domain adaptation approach, termed as self-paced transfer classifier learning (SP-TCL), to address the above issues, which could be regarded as a well-performing baseline for several generalized domain adaptation tasks. The proposed model is established upon the self-paced learning scheme, seeking a preferable classifier for the target domain. Specifically, SP-TCL learns to discover faithful knowledge via a carefully designed prudent loss function and simultaneously adapts the learned knowledge to the target domain by iteratively excluding source examples from training under the self-paced fashion. Extensive evaluations on several benchmark datasets demonstrate that SP-TCL significantly outperforms state-of-the-art approaches on several generalized domain adaptation tasks.</description><subject>Adaptation</subject><subject>Annotations</subject><subject>Classifiers</subject><subject>Datasets</subject><subject>Knowledge</subject><subject>Labels</subject><subject>Learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNiksKwjAUAIMgWLR3CLguxMR-cFesIuhCUHRZHu2zptakJmnF29uFB3A1AzMj4nEhFkGy5HxCfGtrxhiPYh6GwiOXA4JRUlXUaZpJW-geDd0r_W6wrHBFU3pFeDSf4NS1aHppsaRHME5CQzP9BKloWkLrwEk9aNsaDcV9RsY3aCz6P07JfLs5r3fBkF8dWpfXujNqSLlgMUvCKE6Y-O_6AtR7QNw</recordid><startdate>20240620</startdate><enddate>20240620</enddate><creator>Mengcheng Lan</creator><creator>Meng, Min</creator><creator>Yu, Jun</creator><creator>Wu, Jigang</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>20240620</creationdate><title>Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach</title><author>Mengcheng Lan ; Meng, Min ; Yu, Jun ; Wu, Jigang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30708567803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adaptation</topic><topic>Annotations</topic><topic>Classifiers</topic><topic>Datasets</topic><topic>Knowledge</topic><topic>Labels</topic><topic>Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Mengcheng Lan</creatorcontrib><creatorcontrib>Meng, Min</creatorcontrib><creatorcontrib>Yu, Jun</creatorcontrib><creatorcontrib>Wu, Jigang</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>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>Mengcheng Lan</au><au>Meng, Min</au><au>Yu, Jun</au><au>Wu, Jigang</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach</atitle><jtitle>arXiv.org</jtitle><date>2024-06-20</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels are easy to collect, stimulating a great demand for automatic recognition in a generalized setting, i.e., weakly-supervised partial domain adaptation (WS-PDA), which transfers a classifier from a large source domain with noises in labels to a small unlabeled target domain. As such, the key issues of WS-PDA are: 1) how to sufficiently discover the knowledge from the noisy labeled source domain and the unlabeled target domain, and 2) how to successfully adapt the knowledge across domains. In this paper, we propose a simple yet effective domain adaptation approach, termed as self-paced transfer classifier learning (SP-TCL), to address the above issues, which could be regarded as a well-performing baseline for several generalized domain adaptation tasks. The proposed model is established upon the self-paced learning scheme, seeking a preferable classifier for the target domain. Specifically, SP-TCL learns to discover faithful knowledge via a carefully designed prudent loss function and simultaneously adapts the learned knowledge to the target domain by iteratively excluding source examples from training under the self-paced fashion. Extensive evaluations on several benchmark datasets demonstrate that SP-TCL significantly outperforms state-of-the-art approaches on several generalized domain adaptation 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, 2024-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_3070856780
source Free E- Journals
subjects Adaptation
Annotations
Classifiers
Datasets
Knowledge
Labels
Learning
title Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T07%3A23%3A18IST&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=Learning%20to%20Discover%20Knowledge:%20A%20Weakly-Supervised%20Partial%20Domain%20Adaptation%20Approach&rft.jtitle=arXiv.org&rft.au=Mengcheng%20Lan&rft.date=2024-06-20&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3070856780%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3070856780&rft_id=info:pmid/&rfr_iscdi=true