Revisiting Metric Learning for SPD Matrix Based Visual Representation
The success of many visual recognition tasks largely depends on a good similarity measure, and distance metric learning plays an important role in this regard. Meanwhile, Symmetric Positive Definite (SPD) matrix is receiving increased attention for feature representation in multiple computer vision...
Saved in:
Published in | 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 7111 - 7119 |
---|---|
Main Authors | , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.07.2017
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The success of many visual recognition tasks largely depends on a good similarity measure, and distance metric learning plays an important role in this regard. Meanwhile, Symmetric Positive Definite (SPD) matrix is receiving increased attention for feature representation in multiple computer vision applications. However, distance metric learning on SPD matrices has not been sufficiently researched. A few existing works approached this by learning either d 2 × p or d × k transformation matrix for d× d SPD matrices. Different from these methods, this paper proposes a new member to the family of distance metric learning for SPD matrices. It learns only d parameters to adjust the eigenvalues of the SPD matrices through an efficient optimisation scheme. Also, it is shown that the proposed method can be interpreted as learning a sample-specific transformation matrix, instead of the fixed transformation matrix learned for all the samples in the existing works. The optimised d parameters can be used to massage the SPD matrices for better discrimination while still keeping them in the original space. From this perspective, the proposed method complements, rather than competes with, the existing linear-transformation-based methods, as the latter can always be applied to the output of the former to perform distance metric learning in further. The proposed method has been tested on multiple SPD-based visual representation data sets used in the literature, and the results demonstrate its interesting properties and attractive performance. |
---|---|
AbstractList | The success of many visual recognition tasks largely depends on a good similarity measure, and distance metric learning plays an important role in this regard. Meanwhile, Symmetric Positive Definite (SPD) matrix is receiving increased attention for feature representation in multiple computer vision applications. However, distance metric learning on SPD matrices has not been sufficiently researched. A few existing works approached this by learning either d 2 × p or d × k transformation matrix for d× d SPD matrices. Different from these methods, this paper proposes a new member to the family of distance metric learning for SPD matrices. It learns only d parameters to adjust the eigenvalues of the SPD matrices through an efficient optimisation scheme. Also, it is shown that the proposed method can be interpreted as learning a sample-specific transformation matrix, instead of the fixed transformation matrix learned for all the samples in the existing works. The optimised d parameters can be used to massage the SPD matrices for better discrimination while still keeping them in the original space. From this perspective, the proposed method complements, rather than competes with, the existing linear-transformation-based methods, as the latter can always be applied to the output of the former to perform distance metric learning in further. The proposed method has been tested on multiple SPD-based visual representation data sets used in the literature, and the results demonstrate its interesting properties and attractive performance. |
Author | Yinghuan Shi Jianjia Zhang Yang Gao Lei Wang Luping Zhou |
Author_xml | – sequence: 1 surname: Luping Zhou fullname: Luping Zhou email: lupingz@uow.edu.au organization: Univ. of Wollongong, Wollongong, NSW, Australia – sequence: 2 surname: Lei Wang fullname: Lei Wang email: leiw@uow.edu.au organization: Univ. of Wollongong, Wollongong, NSW, Australia – sequence: 3 surname: Jianjia Zhang fullname: Jianjia Zhang email: seuzjj@gmail.com organization: CSIRO, Sydney, NSW, Australia – sequence: 4 surname: Yinghuan Shi fullname: Yinghuan Shi email: syh@nju.edu.cn organization: Nanjing Univ., Nanjing, China – sequence: 5 surname: Yang Gao fullname: Yang Gao email: gaoy@nju.edu.cn organization: Nanjing Univ., Nanjing, China |
BookMark | eNotj01Lw0AYhFeoYFM9evKyfyBxvz-OGlsVUixRey2b5I2s1E3ZjaL_3hQ9DMM8h2EmQ7MwBEDokpKCUmKvy-2mLhihutCSnaCMSm4UEVKLGZpToniuLLVnKEvpnRDGNSNztKzhyyc_-vCG1zBG3-IKXAzH3A8RP2_u8NpN_BvfugQd3vr06fa4hkOEBGF0ox_COTrt3T7Bxb8v0Otq-VI-5NXT_WN5U-WeajnmBpq2b1rFjSai6TvrGgvEgmS9UxympaZpmRCubwwTuu246hR3kwiRygq-QFd_vR4AdofoP1z82Rl6vCP5L-UoS64 |
CODEN | IEEPAD |
ContentType | Conference Proceeding |
DBID | 6IE 6IH CBEJK RIE RIO |
DOI | 10.1109/CVPR.2017.752 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Xplore IEEE Proceedings Order Plans (POP) 1998-present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Applied Sciences Computer Science |
EISBN | 1538604574 9781538604571 |
EndPage | 7119 |
ExternalDocumentID | 8100235 |
Genre | orig-research |
GroupedDBID | 23M 29F 29O 6IE 6IH 6IK ACGFS ALMA_UNASSIGNED_HOLDINGS CBEJK G8K IPLJI JC5 M43 RIE RIG RIO RNS |
ID | FETCH-LOGICAL-i175t-8ebcfbc638704bfd9ab9e09e52fa63e5748bc244afb8247cd36d63ad630056943 |
IEDL.DBID | RIE |
ISSN | 1063-6919 |
IngestDate | Wed Jun 26 19:27:39 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i175t-8ebcfbc638704bfd9ab9e09e52fa63e5748bc244afb8247cd36d63ad630056943 |
PageCount | 9 |
ParticipantIDs | ieee_primary_8100235 |
PublicationCentury | 2000 |
PublicationDate | 2017-July |
PublicationDateYYYYMMDD | 2017-07-01 |
PublicationDate_xml | – month: 07 year: 2017 text: 2017-July |
PublicationDecade | 2010 |
PublicationTitle | 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
PublicationTitleAbbrev | CVPR |
PublicationYear | 2017 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0023720 |
Score | 2.1593173 |
Snippet | The success of many visual recognition tasks largely depends on a good similarity measure, and distance metric learning plays an important role in this regard.... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 7111 |
SubjectTerms | Covariance matrices Eigenvalues and eigenfunctions Euclidean distance Learning systems Visualization |
Title | Revisiting Metric Learning for SPD Matrix Based Visual Representation |
URI | https://ieeexplore.ieee.org/document/8100235 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3LT8IwHG6AkydUML7Tg0c3KOv6uIoQYjJDUAg30qchGjCyJca_3rYbYIwHb8tvhzVtmu-39nsAcIOxkQ51k4iilEbY9QCRdCgbaasRlhoLSrzAOXskoyl-mKfzGrjdaWGMMYF8ZmL_GO7y9VoV_qisw1CwZ6mDOuv2Sq3W7ufKp62Em02SRIQjvvfT7PRn44kncdGYen3RjxSVACLDJsi2ny-5I69xkctYff1yZvzv-A5Bey_Xg-MdEB2Bmlkdg2bVX8Jq925caRvhsK21wGAS1OWe-wwzH66lYOW4-gJdOwufxvcw8y7-n_DO4Z2Gs-WmEG9wEgi0lW5p1QbT4eC5P4qqZIVo6dqFPGJGKiuV23u0i6XVXEhuutykPStIYlKKmVQO-IWVrIep0gnRJBHa-3OlhOPkBDRW65U5BZAgYph177UwmCMjJMIqldQyRLiy7Ay0_EQt3kvzjEU1R-d_ly_AgV-okg97CRr5R2GuHOrn8jos9zdOW6uw |
link.rule.ids | 310,311,786,790,795,796,802,23958,23959,25170,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NT8IwGH6DeNATKhi_7cGjBcq6druKEFRGCALhRtaPGaIZRrbE-OtttwHGePDWvL00bZrn3fp8ANxQqoVBXQdz4nJMTQ-AhUFZrCJFqFA05MwKnIMB603o48ydleB2o4XRWmfkM123w-wtXy1lan-VNTyS2bPswK7B-SbP1Vqbzyubt5K9bTIHM5_4W0fNRns6HFkaF69zqzD6kaOSwUi3AsF6ATl75LWeJqIuv355M_53hQdQ2wr20HADRYdQ0vERVIoOExX3d2VK6xCHda0KnVGmL7fsZxTYeC2JCs_VF2QaWvQ8vEeB9fH_RHcG8RSaLlZp-IZGGYW2UC7FNZh0O-N2DxfZCnhhGoYEe1rISEhz-3iTikj5ofB109duKwqZo11OPSEN9IeR8FqUS-UwxZxQWYcul_nUOYZyvIz1CSBGmPYiM69CTX2iQ0GodAWPPMJ8GXmnULUbNX_P7TPmxR6d_V2-hr3eOOjP-w-Dp3PYt4eWs2MvoJx8pPrS9ACJuMqO_huJQa8E |
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%3Ajournal&rft.genre=proceeding&rft.title=2017+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.atitle=Revisiting+Metric+Learning+for+SPD+Matrix+Based+Visual+Representation&rft.au=Luping+Zhou&rft.au=Lei+Wang&rft.au=Jianjia+Zhang&rft.au=Yinghuan+Shi&rft.date=2017-07-01&rft.pub=IEEE&rft.issn=1063-6919&rft.spage=7111&rft.epage=7119&rft_id=info:doi/10.1109%2FCVPR.2017.752&rft.externalDocID=8100235 |
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 |