Large scale metric learning from equivalence constraints
In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather tedious optimization procedures are applied that become computationally intractable on a large scale. Further, if one considers the constantly...
Uloženo v:
| Vydáno v: | 2012 IEEE Conference on Computer Vision and Pattern Recognition s. 2288 - 2295 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.06.2012
|
| Témata: | |
| ISBN: | 9781467312264, 1467312266 |
| ISSN: | 1063-6919, 1063-6919 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather tedious optimization procedures are applied that become computationally intractable on a large scale. Further, if one considers the constantly growing amount of data it is often infeasible to specify fully supervised labels for all data points. Instead, it is easier to specify labels in form of equivalence constraints. We introduce a simple though effective strategy to learn a distance metric from equivalence constraints, based on a statistical inference perspective. In contrast to existing methods we do not rely on complex optimization problems requiring computationally expensive iterations. Hence, our method is orders of magnitudes faster than comparable methods. Results on a variety of challenging benchmarks with rather diverse nature demonstrate the power of our method. These include faces in unconstrained environments, matching before unseen object instances and person re-identification across spatially disjoint cameras. In the latter two benchmarks we clearly outperform the state-of-the-art. |
|---|---|
| AbstractList | In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather tedious optimization procedures are applied that become computationally intractable on a large scale. Further, if one considers the constantly growing amount of data it is often infeasible to specify fully supervised labels for all data points. Instead, it is easier to specify labels in form of equivalence constraints. We introduce a simple though effective strategy to learn a distance metric from equivalence constraints, based on a statistical inference perspective. In contrast to existing methods we do not rely on complex optimization problems requiring computationally expensive iterations. Hence, our method is orders of magnitudes faster than comparable methods. Results on a variety of challenging benchmarks with rather diverse nature demonstrate the power of our method. These include faces in unconstrained environments, matching before unseen object instances and person re-identification across spatially disjoint cameras. In the latter two benchmarks we clearly outperform the state-of-the-art. |
| Author | Roth, P. M. Kostinger, M. Bischof, H. Wohlhart, P. Hirzer, M. |
| Author_xml | – sequence: 1 givenname: M. surname: Kostinger fullname: Kostinger, M. email: koestinger@icg.tugraz.at organization: Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria – sequence: 2 givenname: M. surname: Hirzer fullname: Hirzer, M. email: hirzer@icg.tugraz.at organization: Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria – sequence: 3 givenname: P. surname: Wohlhart fullname: Wohlhart, P. email: wohlhart@icg.tugraz.at organization: Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria – sequence: 4 givenname: P. M. surname: Roth fullname: Roth, P. M. email: pmroth@icg.tugraz.at organization: Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria – sequence: 5 givenname: H. surname: Bischof fullname: Bischof, H. email: bischof@icg.tugraz.at organization: Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria |
| BookMark | eNpNkM1KxDAUhaOO4MzYBxA3fYGO-WmT3KUUR4WCIup2SNLbIdKmmlTBt7fgCJ7NWXwfZ3FWZBHGgIRcMLphjMJV_fr4tOGU8Y3kpQIBR2TFSqkE41zzY7JkVIpCAoMTkoHSf0yWi3_sjGQpvdE5s0GBL4luTNxjnpzpMR9wit7lPZoYfNjnXRyHHD8-_ddMg8PcjSFN0fgwpXNy2pk-YXboNXnZ3jzXd0XzcHtfXzeFZ6qaCqdaKToLrAVLuQbVOUsRbWmtBNRaOSuqqmyB26qU2rbglDUdSio0tVaINbn83fWIuHuPfjDxe3c4QfwArbJOKw |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR.2012.6247939 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Computer Science |
| EISBN | 1467312282 1467312274 9781467312271 9781467312288 |
| EISSN | 1063-6919 |
| EndPage | 2295 |
| ExternalDocumentID | 6247939 |
| Genre | orig-research |
| GroupedDBID | 23M 29F 29O 6IE 6IH 6IK ABDPE ACGFS ALMA_UNASSIGNED_HOLDINGS CBEJK IPLJI M43 RIE RIO RNS |
| ID | FETCH-LOGICAL-i175t-c7d63fb91d9b02897fcb0eeb4bb69e887cb3554d92b5468bd9c7bafe60380bb33 |
| IEDL.DBID | RIE |
| ISBN | 9781467312264 1467312266 |
| ISICitedReferencesCount | 976 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000309166202057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1063-6919 |
| IngestDate | Wed Aug 27 04:27:19 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i175t-c7d63fb91d9b02897fcb0eeb4bb69e887cb3554d92b5468bd9c7bafe60380bb33 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_6247939 |
| PublicationCentury | 2000 |
| PublicationDate | 2012-June |
| PublicationDateYYYYMMDD | 2012-06-01 |
| PublicationDate_xml | – month: 06 year: 2012 text: 2012-June |
| PublicationDecade | 2010 |
| PublicationTitle | 2012 IEEE Conference on Computer Vision and Pattern Recognition |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2012 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0000781092 ssj0023720 ssj0003211698 |
| Score | 2.4602537 |
| Snippet | In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 2288 |
| SubjectTerms | Benchmark testing Measurement Optimization Scalability Support vector machines Training |
| Title | Large scale metric learning from equivalence constraints |
| URI | https://ieeexplore.ieee.org/document/6247939 |
| WOSCitedRecordID | wos000309166202057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6AePDkA4zv9ODRwj6n7ZlIPBBCjBpuZNudNRwEhcXfb6eUNSZevG3nsN1M2-2038z3MXYnc6wyABRY6EJkGrXQldEiKnUEWhGJmKfMH8vJRM1metpi900tDCL65DPs06PH8suV3dJV2QASugfSbdaWEna1Ws19CpHWRAEhpHbqTjagG0QhITUWj3xCKkDH2hd5gUxjF3_AnvsptLMAf7oXDoav0yfKAEv6ofdfMix-Fxod_e_7j1nvp5yPT5uN6oS1cHnKjkL8ycPq3jjTXuJhb-syNaZMcb5xI4n8ndS3LA9CE2-cSlM4fm4Xbrb6TiwFm6Q5UW967GX08Dx8FEFsQSxcBFELK0tI3SjFpTaEPsrKmgjRZMaARvcrsoZCk1InJs9AmVJbaYoKIUpVZEyanrHOcrXEc8bzqDQyjxFKRXyEsQJ3rHIr3ShrbGyLC9Yl38w_dnwa8-CWy7_NV-yQ3L9Lz7pmnXq9xRt2YL_qxWZ96yfBN3AWqSw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVKQYKpQIv4JgMjbp0vJ54rqiJCVaGCulWxfUEdaKFJ-f34XDcIiYUtviFWfHZ89rt7j5DbJIYi4hwo5CKnkQBBRSEFZVowLlIkEbOU-VkyGqXTqRg3yF1dCwMANvkMuvhosXy9VGu8KuvxAO-BxA7ZjaMoYJtqrfpGBWlrmMMIsR2asw0XNaYQoB6LxT55SLnwhS3z4knomwiEb9mfXDtyAKh5Ya__On7GHLCg6_r_JcRi96FB639fcEg6PwV93rjeqo5IAxbHpOUiUM-t79KYtiIPW1ubpBnminul8SV476i_pTwnNfHmYXGKB5_ruZmvthOF4SaqTlRlh7wM7if9IXVyC3RuYoiKqkTz0PjJ10Ii_pgUSjIAGUnJBZifkZIYnGgRyDjiqdRCJTIvgLMwZVKG4QlpLpYLOCVezLRMYh-4TpGR0E-5OViZtS5TJZWv8jPSxrGZfWwYNWZuWM7_Nt-Q_eHkKZtlD6PHC3KArtgka12SZrVawxXZU1_VvFxd2wnxDXRWrHM |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2012+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=Large+scale+metric+learning+from+equivalence+constraints&rft.au=Kostinger%2C+M.&rft.au=Hirzer%2C+M.&rft.au=Wohlhart%2C+P.&rft.au=Roth%2C+P.+M.&rft.date=2012-06-01&rft.pub=IEEE&rft.isbn=9781467312264&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=2288&rft.epage=2295&rft_id=info:doi/10.1109%2FCVPR.2012.6247939&rft.externalDocID=6247939 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon |