Self-Supervised Multi-Object Tracking with Path Consistency

In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can obser...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-04
Hauptverfasser: Lu, Zijia, Shuai, Bing, Chen, Yanbei, Xu, Zhenlin, Modolo, Davide
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 Lu, Zijia
Shuai, Bing
Chen, Yanbei
Xu, Zhenlin
Modolo, Davide
description In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3034834731</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3034834731</sourcerecordid><originalsourceid>FETCH-proquest_journals_30348347313</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwDk7NSdMNLi1ILSrLLE5NUfAtzSnJ1PVPykpNLlEIKUpMzs7MS1cozyzJUAhIBBLO-XnFmcUlqXnJlTwMrGmJOcWpvFCam0HZzTXE2UO3oCi_sDS1uCQ-K7-0KA8oFW9sYGxiYWxibmxoTJwqAPi3NyY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3034834731</pqid></control><display><type>article</type><title>Self-Supervised Multi-Object Tracking with Path Consistency</title><source>Free E- Journals</source><creator>Lu, Zijia ; Shuai, Bing ; Chen, Yanbei ; Xu, Zhenlin ; Modolo, Davide</creator><creatorcontrib>Lu, Zijia ; Shuai, Bing ; Chen, Yanbei ; Xu, Zhenlin ; Modolo, Davide</creatorcontrib><description>In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Consistency ; Frames ; Matching ; Multiple target tracking</subject><ispartof>arXiv.org, 2024-04</ispartof><rights>2024. 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>780,784</link.rule.ids></links><search><creatorcontrib>Lu, Zijia</creatorcontrib><creatorcontrib>Shuai, Bing</creatorcontrib><creatorcontrib>Chen, Yanbei</creatorcontrib><creatorcontrib>Xu, Zhenlin</creatorcontrib><creatorcontrib>Modolo, Davide</creatorcontrib><title>Self-Supervised Multi-Object Tracking with Path Consistency</title><title>arXiv.org</title><description>In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.</description><subject>Consistency</subject><subject>Frames</subject><subject>Matching</subject><subject>Multiple target tracking</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>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwDk7NSdMNLi1ILSrLLE5NUfAtzSnJ1PVPykpNLlEIKUpMzs7MS1cozyzJUAhIBBLO-XnFmcUlqXnJlTwMrGmJOcWpvFCam0HZzTXE2UO3oCi_sDS1uCQ-K7-0KA8oFW9sYGxiYWxibmxoTJwqAPi3NyY</recordid><startdate>20240408</startdate><enddate>20240408</enddate><creator>Lu, Zijia</creator><creator>Shuai, Bing</creator><creator>Chen, Yanbei</creator><creator>Xu, Zhenlin</creator><creator>Modolo, Davide</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>20240408</creationdate><title>Self-Supervised Multi-Object Tracking with Path Consistency</title><author>Lu, Zijia ; Shuai, Bing ; Chen, Yanbei ; Xu, Zhenlin ; Modolo, Davide</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30348347313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Consistency</topic><topic>Frames</topic><topic>Matching</topic><topic>Multiple target tracking</topic><toplevel>online_resources</toplevel><creatorcontrib>Lu, Zijia</creatorcontrib><creatorcontrib>Shuai, Bing</creatorcontrib><creatorcontrib>Chen, Yanbei</creatorcontrib><creatorcontrib>Xu, Zhenlin</creatorcontrib><creatorcontrib>Modolo, Davide</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 (ProQuest)</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>Lu, Zijia</au><au>Shuai, Bing</au><au>Chen, Yanbei</au><au>Xu, Zhenlin</au><au>Modolo, Davide</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Self-Supervised Multi-Object Tracking with Path Consistency</atitle><jtitle>arXiv.org</jtitle><date>2024-04-08</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.</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, 2024-04
issn 2331-8422
language eng
recordid cdi_proquest_journals_3034834731
source Free E- Journals
subjects Consistency
Frames
Matching
Multiple target tracking
title Self-Supervised Multi-Object Tracking with Path Consistency
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T08%3A11%3A15IST&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=Self-Supervised%20Multi-Object%20Tracking%20with%20Path%20Consistency&rft.jtitle=arXiv.org&rft.au=Lu,%20Zijia&rft.date=2024-04-08&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3034834731%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3034834731&rft_id=info:pmid/&rfr_iscdi=true