Deep Cosine Metric Learning for Person Re-Identification
| العنوان: | Deep Cosine Metric Learning for Person Re-Identification |
|---|---|
| المؤلفون: | Alex Bewley, Nicolai Wojke |
| المصدر: | WACV |
| بيانات النشر: | IEEE, 2018. |
| سنة النشر: | 2018 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, Feature vector, Computer Vision and Pattern Recognition (cs.CV), Feature extraction, Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, k-nearest neighbors algorithm, Machine Learning (cs.LG), Datenerfassung und Informationsgewinnung, 0202 electrical engineering, electronic engineering, information engineering, Person Re-Identification, 0105 earth and related environmental sciences, business.industry, Cosine similarity, Convolutional Neural Networks, Pattern recognition, ComputingMethodologies_PATTERNRECOGNITION, Test set, Metric (mathematics), Softmax function, Embedding, 020201 artificial intelligence & image processing, Artificial intelligence, business, Metric Learning |
| الوصف: | Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss. |
| وصف الملف: | application/pdf |
| اللغة: | English |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08cabc2168313a97c4e49e3d7844703e https://elib.dlr.de/116408/ |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....08cabc2168313a97c4e49e3d7844703e |
| قاعدة البيانات: | OpenAIRE |
| ResultId |
1 |
|---|---|
| Header |
edsair OpenAIRE edsair.doi.dedup.....08cabc2168313a97c4e49e3d7844703e 809 3 unknown 808.885498046875 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsair&AN=edsair.doi.dedup.....08cabc2168313a97c4e49e3d7844703e&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08cabc2168313a97c4e49e3d7844703e# [Name] => EDS - OpenAIRE [Category] => fullText [Text] => View record in OpenAIRE [MouseOverText] => View record in OpenAIRE ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Deep Cosine Metric Learning for Person Re-Identification
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Alex+Bewley%22">Alex Bewley</searchLink><br /><searchLink fieldCode="AR" term="%22Nicolai+Wojke%22">Nicolai Wojke</searchLink> ) Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => WACV ) Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => IEEE, 2018. ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2018 ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22FOS%3A+Computer+and+information+sciences%22">FOS: Computer and information sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+science%22">Computer science</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+vector%22">Feature vector</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Vision+and+Pattern+Recognition+%28cs%2ECV%29%22">Computer Vision and Pattern Recognition (cs.CV)</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink><br /><searchLink fieldCode="DE" term="%2202+engineering+and+technology%22">02 engineering and technology</searchLink><br /><searchLink fieldCode="DE" term="%22010501+environmental+sciences%22">010501 environmental sciences</searchLink><br /><searchLink fieldCode="DE" term="%2201+natural+sciences%22">01 natural sciences</searchLink><br /><searchLink fieldCode="DE" term="%22k-nearest+neighbors+algorithm%22">k-nearest neighbors algorithm</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+Learning+%28cs%2ELG%29%22">Machine Learning (cs.LG)</searchLink><br /><searchLink fieldCode="DE" term="%22Datenerfassung+und+Informationsgewinnung%22">Datenerfassung und Informationsgewinnung</searchLink><br /><searchLink fieldCode="DE" term="%220202+electrical+engineering%2C+electronic+engineering%2C+information+engineering%22">0202 electrical engineering, electronic engineering, information engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Person+Re-Identification%22">Person Re-Identification</searchLink><br /><searchLink fieldCode="DE" term="%220105+earth+and+related+environmental+sciences%22">0105 earth and related environmental sciences</searchLink><br /><searchLink fieldCode="DE" term="%22business%2Eindustry%22">business.industry</searchLink><br /><searchLink fieldCode="DE" term="%22Cosine+similarity%22">Cosine similarity</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+Neural+Networks%22">Convolutional Neural Networks</searchLink><br /><searchLink fieldCode="DE" term="%22Pattern+recognition%22">Pattern recognition</searchLink><br /><searchLink fieldCode="DE" term="%22ComputingMethodologies%5FPATTERNRECOGNITION%22">ComputingMethodologies_PATTERNRECOGNITION</searchLink><br /><searchLink fieldCode="DE" term="%22Test+set%22">Test set</searchLink><br /><searchLink fieldCode="DE" term="%22Metric+%28mathematics%29%22">Metric (mathematics)</searchLink><br /><searchLink fieldCode="DE" term="%22Softmax+function%22">Softmax function</searchLink><br /><searchLink fieldCode="DE" term="%22Embedding%22">Embedding</searchLink><br /><searchLink fieldCode="DE" term="%22020201+artificial+intelligence+%26+image+processing%22">020201 artificial intelligence & image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22business%22">business</searchLink><br /><searchLink fieldCode="DE" term="%22Metric+Learning%22">Metric Learning</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss. ) Array ( [Name] => Format [Label] => File Description [Group] => SrcInfo [Data] => application/pdf ) Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => English ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08cabc2168313a97c4e49e3d7844703e" linkWindow="_blank">https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08cabc2168313a97c4e49e3d7844703e</link><br /><link linkTarget="URL" linkTerm="https://elib.dlr.de/116408/" linkWindow="_blank">https://elib.dlr.de/116408/</link> ) Array ( [Name] => Copyright [Label] => Rights [Group] => Cpyrght [Data] => OPEN ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsair.doi.dedup.....08cabc2168313a97c4e49e3d7844703e ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Languages] => Array
(
[0] => Array
(
[Text] => English
)
)
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => FOS: Computer and information sciences
[Type] => general
)
[1] => Array
(
[SubjectFull] => Computer Science - Machine Learning
[Type] => general
)
[2] => Array
(
[SubjectFull] => Computer science
[Type] => general
)
[3] => Array
(
[SubjectFull] => Feature vector
[Type] => general
)
[4] => Array
(
[SubjectFull] => Computer Vision and Pattern Recognition (cs.CV)
[Type] => general
)
[5] => Array
(
[SubjectFull] => Feature extraction
[Type] => general
)
[6] => Array
(
[SubjectFull] => Computer Science - Computer Vision and Pattern Recognition
[Type] => general
)
[7] => Array
(
[SubjectFull] => 02 engineering and technology
[Type] => general
)
[8] => Array
(
[SubjectFull] => 010501 environmental sciences
[Type] => general
)
[9] => Array
(
[SubjectFull] => 01 natural sciences
[Type] => general
)
[10] => Array
(
[SubjectFull] => k-nearest neighbors algorithm
[Type] => general
)
[11] => Array
(
[SubjectFull] => Machine Learning (cs.LG)
[Type] => general
)
[12] => Array
(
[SubjectFull] => Datenerfassung und Informationsgewinnung
[Type] => general
)
[13] => Array
(
[SubjectFull] => 0202 electrical engineering, electronic engineering, information engineering
[Type] => general
)
[14] => Array
(
[SubjectFull] => Person Re-Identification
[Type] => general
)
[15] => Array
(
[SubjectFull] => 0105 earth and related environmental sciences
[Type] => general
)
[16] => Array
(
[SubjectFull] => business.industry
[Type] => general
)
[17] => Array
(
[SubjectFull] => Cosine similarity
[Type] => general
)
[18] => Array
(
[SubjectFull] => Convolutional Neural Networks
[Type] => general
)
[19] => Array
(
[SubjectFull] => Pattern recognition
[Type] => general
)
[20] => Array
(
[SubjectFull] => ComputingMethodologies_PATTERNRECOGNITION
[Type] => general
)
[21] => Array
(
[SubjectFull] => Test set
[Type] => general
)
[22] => Array
(
[SubjectFull] => Metric (mathematics)
[Type] => general
)
[23] => Array
(
[SubjectFull] => Softmax function
[Type] => general
)
[24] => Array
(
[SubjectFull] => Embedding
[Type] => general
)
[25] => Array
(
[SubjectFull] => 020201 artificial intelligence & image processing
[Type] => general
)
[26] => Array
(
[SubjectFull] => Artificial intelligence
[Type] => general
)
[27] => Array
(
[SubjectFull] => business
[Type] => general
)
[28] => Array
(
[SubjectFull] => Metric Learning
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Deep Cosine Metric Learning for Person Re-Identification
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Alex Bewley
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Nicolai Wojke
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 01
[M] => 01
[Type] => published
[Y] => 2018
)
)
[Identifiers] => Array
(
[0] => Array
(
[Type] => issn-locals
[Value] => edsair
)
[1] => Array
(
[Type] => issn-locals
[Value] => edsairFT
)
)
)
)
)
)
)
|
| IllustrationInfo |