Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification

Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-01
Hauptverfasser: Tang, Chunren, Xue, Dingyu, Chen, Dongyue
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 Tang, Chunren
Xue, Dingyu
Chen, Dongyue
description Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve these problems, this paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. At first, we propose a Sample Dropout (SD) method to prevent the training of the model from falling into the vicious circle caused by samples that are frequently assigned with noisy pseudo labels. In addition, we put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture, which can significantly improve the generalization ability of the feature representation on the target domain. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2622854384</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2622854384</sourcerecordid><originalsourceid>FETCH-proquest_journals_26228543843</originalsourceid><addsrcrecordid>eNqNjLsKwjAUQIMgKOo_XHAu1KTVrqIWBwfxMZdgb-0tbRLzqPj3dvADnM5wDmfEplyIVZQlnE_YwrkmjmO-3vA0FVNW5yh9sAh76tE68h84obSK1BPe5Gu4ys60g7ba6OCh0hbuygWDtieHJex1J0nBtpTGDws4Dxet4IIRlag8VfSQnrSas3ElW4eLH2dsmR9uu2NkrH4FdL5odLBqUAVfc56licgS8V_1BaHcSG4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2622854384</pqid></control><display><type>article</type><title>Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification</title><source>Free E- Journals</source><creator>Tang, Chunren ; Xue, Dingyu ; Chen, Dongyue</creator><creatorcontrib>Tang, Chunren ; Xue, Dingyu ; Chen, Dongyue</creatorcontrib><description>Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve these problems, this paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. At first, we propose a Sample Dropout (SD) method to prevent the training of the model from falling into the vicious circle caused by samples that are frequently assigned with noisy pseudo labels. In addition, we put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture, which can significantly improve the generalization ability of the feature representation on the target domain. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptive sampling ; Clustering ; Domains ; Labels ; Learning ; Representations ; Training</subject><ispartof>arXiv.org, 2022-01</ispartof><rights>2022. 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>Tang, Chunren</creatorcontrib><creatorcontrib>Xue, Dingyu</creatorcontrib><creatorcontrib>Chen, Dongyue</creatorcontrib><title>Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification</title><title>arXiv.org</title><description>Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve these problems, this paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. At first, we propose a Sample Dropout (SD) method to prevent the training of the model from falling into the vicious circle caused by samples that are frequently assigned with noisy pseudo labels. In addition, we put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture, which can significantly improve the generalization ability of the feature representation on the target domain. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.</description><subject>Adaptive sampling</subject><subject>Clustering</subject><subject>Domains</subject><subject>Labels</subject><subject>Learning</subject><subject>Representations</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjLsKwjAUQIMgKOo_XHAu1KTVrqIWBwfxMZdgb-0tbRLzqPj3dvADnM5wDmfEplyIVZQlnE_YwrkmjmO-3vA0FVNW5yh9sAh76tE68h84obSK1BPe5Gu4ys60g7ba6OCh0hbuygWDtieHJex1J0nBtpTGDws4Dxet4IIRlag8VfSQnrSas3ElW4eLH2dsmR9uu2NkrH4FdL5odLBqUAVfc56licgS8V_1BaHcSG4</recordid><startdate>20220125</startdate><enddate>20220125</enddate><creator>Tang, Chunren</creator><creator>Xue, Dingyu</creator><creator>Chen, Dongyue</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>20220125</creationdate><title>Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification</title><author>Tang, Chunren ; Xue, Dingyu ; Chen, Dongyue</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26228543843</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Adaptive sampling</topic><topic>Clustering</topic><topic>Domains</topic><topic>Labels</topic><topic>Learning</topic><topic>Representations</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Tang, Chunren</creatorcontrib><creatorcontrib>Xue, Dingyu</creatorcontrib><creatorcontrib>Chen, Dongyue</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>Tang, Chunren</au><au>Xue, Dingyu</au><au>Chen, Dongyue</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification</atitle><jtitle>arXiv.org</jtitle><date>2022-01-25</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve these problems, this paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. At first, we propose a Sample Dropout (SD) method to prevent the training of the model from falling into the vicious circle caused by samples that are frequently assigned with noisy pseudo labels. In addition, we put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture, which can significantly improve the generalization ability of the feature representation on the target domain. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.</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, 2022-01
issn 2331-8422
language eng
recordid cdi_proquest_journals_2622854384
source Free E- Journals
subjects Adaptive sampling
Clustering
Domains
Labels
Learning
Representations
Training
title Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T03%3A19%3A58IST&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=Feature%20Diversity%20Learning%20with%20Sample%20Dropout%20for%20Unsupervised%20Domain%20Adaptive%20Person%20Re-identification&rft.jtitle=arXiv.org&rft.au=Tang,%20Chunren&rft.date=2022-01-25&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2622854384%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2622854384&rft_id=info:pmid/&rfr_iscdi=true