Comparison of Generative and Discriminative Techniques for Object Detection and Classification
Identifieur interne : 001097 ( Main/Exploration ); précédent : 001096; suivant : 001098Comparison of Generative and Discriminative Techniques for Object Detection and Classification
Auteurs : Ilkay Ulusoy [Turquie] ; M. Bishop [Royaume-Uni]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2006.
Abstract
Abstract: Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining the strengths of generative and discriminative approaches.
Url:
DOI: 10.1007/11957959_9
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001936
- to stream Istex, to step Curation: 001836
- to stream Istex, to step Checkpoint: 000A70
- to stream Main, to step Merge: 001114
- to stream Main, to step Curation: 001097
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Comparison of Generative and Discriminative Techniques for Object Detection and Classification</title>
<author><name sortKey="Ulusoy, Ilkay" sort="Ulusoy, Ilkay" uniqKey="Ulusoy I" first="Ilkay" last="Ulusoy">Ilkay Ulusoy</name>
</author>
<author><name sortKey="Bishop, M" sort="Bishop, M" uniqKey="Bishop M" first="M." last="Bishop">M. Bishop</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:8D3835A0B89B1CD09D1F7052EF889E831D54A06A</idno>
<date when="2006" year="2006">2006</date>
<idno type="doi">10.1007/11957959_9</idno>
<idno type="url">https://api.istex.fr/document/8D3835A0B89B1CD09D1F7052EF889E831D54A06A/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">001936</idno>
<idno type="wicri:Area/Istex/Curation">001836</idno>
<idno type="wicri:Area/Istex/Checkpoint">000A70</idno>
<idno type="wicri:doubleKey">0302-9743:2006:Ulusoy I:comparison:of:generative</idno>
<idno type="wicri:Area/Main/Merge">001114</idno>
<idno type="wicri:Area/Main/Curation">001097</idno>
<idno type="wicri:Area/Main/Exploration">001097</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Comparison of Generative and Discriminative Techniques for Object Detection and Classification</title>
<author><name sortKey="Ulusoy, Ilkay" sort="Ulusoy, Ilkay" uniqKey="Ulusoy I" first="Ilkay" last="Ulusoy">Ilkay Ulusoy</name>
<affiliation wicri:level="1"><country xml:lang="fr">Turquie</country>
<wicri:regionArea>Computer Vision and Intelligent Systems Research Lab., METU, 06531, Ankara</wicri:regionArea>
<wicri:noRegion>Ankara</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Bishop, M" sort="Bishop, M" uniqKey="Bishop M" first="M." last="Bishop">M. Bishop</name>
<affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country>
<wicri:regionArea>Microsoft Research, 7 J J Thompson Avenue, Cambridge</wicri:regionArea>
<wicri:noRegion>Cambridge</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2006</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">8D3835A0B89B1CD09D1F7052EF889E831D54A06A</idno>
<idno type="DOI">10.1007/11957959_9</idno>
<idno type="ChapterID">9</idno>
<idno type="ChapterID">Chap9</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining the strengths of generative and discriminative approaches.</div>
</front>
</TEI>
<affiliations><list><country><li>Royaume-Uni</li>
<li>Turquie</li>
</country>
</list>
<tree><country name="Turquie"><noRegion><name sortKey="Ulusoy, Ilkay" sort="Ulusoy, Ilkay" uniqKey="Ulusoy I" first="Ilkay" last="Ulusoy">Ilkay Ulusoy</name>
</noRegion>
</country>
<country name="Royaume-Uni"><noRegion><name sortKey="Bishop, M" sort="Bishop, M" uniqKey="Bishop M" first="M." last="Bishop">M. Bishop</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001097 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001097 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:8D3835A0B89B1CD09D1F7052EF889E831D54A06A |texte= Comparison of Generative and Discriminative Techniques for Object Detection and Classification }}
This area was generated with Dilib version V0.6.32. |