AustralieFrV1, PascalFrancis, Corpus, bibRecord, 002698

Unsupervised Object Discovery: A Comparison

Identifieur interne : 002698 ( PascalFrancis/Corpus ); précédent : 002697; suivant : 002699

Unsupervised Object Discovery: A Comparison

Auteurs : Tinne Tuytelaars ; Christoph H. Lampert ; Matthew B. Blaschko ; Wray Buntine

Source :

International journal of computer vision [ 0920-5691 ] ; 2010.

RBID : Pascal:10-0236313

Descripteurs français

Pascal (Inist)
- Traitement image, Banque image, Vision ordinateur, Modèle variable latente, Modélisation, Méthode spectrale, Analyse amas, ., Reconnaissance objet, Apprentissage non supervisé.

English descriptors

KwdEn :
- Cluster analysis, Computer vision, Image databank, Image processing, Latent variable model, Modeling, Object recognition, Spectral method, Unsupervised learning.

Abstract

The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

A01	`01`	`1`		`@0 0920-5691`
A03		`1`		`@0 Int. j. comput. vis.`
A05				`@2 88`
A06				`@2 2`
A08	`01`	`1`	`ENG`	`@1 Unsupervised Object Discovery: A Comparison`
A09	`01`	`1`	`ENG`	`@1 Probabilistic Models for Image Understanding`
A11	`01`	`1`		`@1 TUYTELAARS (Tinne)`
A11	`02`	`1`		`@1 LAMPERT (Christoph H.)`
A11	`03`	`1`		`@1 BLASCHKO (Matthew B.)`
A11	`04`	`1`		`@1 BUNTINE (Wray)`
A12	`01`	`1`		`@1 TRIGGS (Bill) @9 ed.`
A12	`02`	`1`		`@1 WILLIAMS (Christopher K. I.) @9 ed.`
A14	`01`			`@1 ESAT-PSI, K.U. Leuven, Kasteelpark Arenberg 10, bus 2241 @2 Leuven 3001 @3 BEL @Z 1 aut.`
A14	`02`			`@1 Max Planck Institute for Biological Cybernetics @2 Tübingen @3 DEU @Z 2 aut. @Z 3 aut.`
A14	`03`			`@1 University of Oxford @2 Oxford @3 GBR @Z 3 aut.`
A14	`04`			`@1 NICTA @2 Canberra @3 AUS @Z 4 aut.`
A14	`05`			`@1 Australian National University @2 Canberra @3 AUS @Z 4 aut.`
A15	`01`			`@1 Laboratoire Jean Kuntzman @2 Grenoble @3 FRA @Z 1 aut.`
A15	`02`			`@1 University of Edinburgh @2 Edinburgh @3 GBR @Z 2 aut.`
A20				`@1 284-302`
A21				`@1 2010`
A23	`01`			`@0 ENG`
A43	`01`			`@1 INIST @2 21361 @5 354000182008660070`
A44				`@0 0000 @1 © 2010 INIST-CNRS. All rights reserved.`
A45				`@0 3/4 p.`
A47	`01`	`1`		`@0 10-0236313`
A60				`@1 P`
A61				`@0 A`
A64	`01`	`1`		`@0 International journal of computer vision`
A66	`01`			`@0 DEU`
C01	`01`		`ENG`	@0 The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.
C02	`01`	`X`		`@0 001D02C03`
C02	`02`	`X`		`@0 001D02B07B`
C03	`01`	`X`	`FRE`	`@0 Traitement image @5 01`
C03	`01`	`X`	`ENG`	`@0 Image processing @5 01`
C03	`01`	`X`	`SPA`	`@0 Procesamiento imagen @5 01`
C03	`02`	`X`	`FRE`	`@0 Banque image @5 06`
C03	`02`	`X`	`ENG`	`@0 Image databank @5 06`
C03	`02`	`X`	`SPA`	`@0 Banco imagen @5 06`
C03	`03`	`X`	`FRE`	`@0 Vision ordinateur @5 07`
C03	`03`	`X`	`ENG`	`@0 Computer vision @5 07`
C03	`03`	`X`	`SPA`	`@0 Visión ordenador @5 07`
C03	`04`	`X`	`FRE`	`@0 Modèle variable latente @5 18`
C03	`04`	`X`	`ENG`	`@0 Latent variable model @5 18`
C03	`04`	`X`	`SPA`	`@0 Modelo variable latente @5 18`
C03	`05`	`X`	`FRE`	`@0 Modélisation @5 23`
C03	`05`	`X`	`ENG`	`@0 Modeling @5 23`
C03	`05`	`X`	`SPA`	`@0 Modelización @5 23`
C03	`06`	`X`	`FRE`	`@0 Méthode spectrale @5 24`
C03	`06`	`X`	`ENG`	`@0 Spectral method @5 24`
C03	`06`	`X`	`SPA`	`@0 Método espectral @5 24`
C03	`07`	`X`	`FRE`	`@0 Analyse amas @5 25`
C03	`07`	`X`	`ENG`	`@0 Cluster analysis @5 25`
C03	`07`	`X`	`SPA`	`@0 Analisis cluster @5 25`
C03	`08`	`X`	`FRE`	`@0 . @4 INC @5 82`
C03	`09`	`X`	`FRE`	`@0 Reconnaissance objet @4 CD @5 96`
C03	`09`	`X`	`ENG`	`@0 Object recognition @4 CD @5 96`
C03	`09`	`X`	`SPA`	`@0 Reconocimiento de objetos @4 CD @5 96`
C03	`10`	`X`	`FRE`	`@0 Apprentissage non supervisé @4 CD @5 97`
C03	`10`	`X`	`ENG`	`@0 Unsupervised learning @4 CD @5 97`
C03	`10`	`X`	`SPA`	`@0 Aprendizaje no supervisado @4 CD @5 97`
N21				`@1 158`
N44	`01`			`@1 OTO`
N82				`@1 OTO`

Format Inist (serveur)

NO :	PASCAL 10-0236313 INIST
ET :	Unsupervised Object Discovery: A Comparison
AU :	TUYTELAARS (Tinne); LAMPERT (Christoph H.); BLASCHKO (Matthew B.); BUNTINE (Wray); TRIGGS (Bill); WILLIAMS (Christopher K. I.)
AF :	ESAT-PSI, K.U. Leuven, Kasteelpark Arenberg 10, bus 2241/Leuven 3001/Belgique (1 aut.); Max Planck Institute for Biological Cybernetics/Tübingen/Allemagne (2 aut., 3 aut.); University of Oxford/Oxford/Royaume-Uni (3 aut.); NICTA/Canberra/Australie (4 aut.); Australian National University/Canberra/Australie (4 aut.); Laboratoire Jean Kuntzman/Grenoble/France (1 aut.); University of Edinburgh/Edinburgh/Royaume-Uni (2 aut.)
DT :	Publication en série; Niveau analytique
SO :	International journal of computer vision; ISSN 0920-5691; Allemagne; Da. 2010; Vol. 88; No. 2; Pp. 284-302; Bibl. 3/4 p.
LA :	Anglais
EA :	The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.
CC :	001D02C03; 001D02B07B
FD :	Traitement image; Banque image; Vision ordinateur; Modèle variable latente; Modélisation; Méthode spectrale; Analyse amas; .; Reconnaissance objet; Apprentissage non supervisé
ED :	Image processing; Image databank; Computer vision; Latent variable model; Modeling; Spectral method; Cluster analysis; Object recognition; Unsupervised learning
SD :	Procesamiento imagen; Banco imagen; Visión ordenador; Modelo variable latente; Modelización; Método espectral; Analisis cluster; Reconocimiento de objetos; Aprendizaje no supervisado
LO :	INIST-21361.354000182008660070
ID :	10-0236313

Links to Exploration step

Pascal:10-0236313

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Unsupervised Object Discovery: A Comparison</title>
<author><name sortKey="Tuytelaars, Tinne" sort="Tuytelaars, Tinne" uniqKey="Tuytelaars T" first="Tinne" last="Tuytelaars">Tinne Tuytelaars</name>
<affiliation><inist:fA14 i1="01"><s1>ESAT-PSI, K.U. Leuven, Kasteelpark Arenberg 10, bus 2241</s1>
<s2>Leuven 3001</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Lampert, Christoph H" sort="Lampert, Christoph H" uniqKey="Lampert C" first="Christoph H." last="Lampert">Christoph H. Lampert</name>
<affiliation><inist:fA14 i1="02"><s1>Max Planck Institute for Biological Cybernetics</s1>
<s2>Tübingen</s2>
<s3>DEU</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Blaschko, Matthew B" sort="Blaschko, Matthew B" uniqKey="Blaschko M" first="Matthew B." last="Blaschko">Matthew B. Blaschko</name>
<affiliation><inist:fA14 i1="02"><s1>Max Planck Institute for Biological Cybernetics</s1>
<s2>Tübingen</s2>
<s3>DEU</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="03"><s1>University of Oxford</s1>
<s2>Oxford</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Buntine, Wray" sort="Buntine, Wray" uniqKey="Buntine W" first="Wray" last="Buntine">Wray Buntine</name>
<affiliation><inist:fA14 i1="04"><s1>NICTA</s1>
<s2>Canberra</s2>
<s3>AUS</s3>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="05"><s1>Australian National University</s1>
<s2>Canberra</s2>
<s3>AUS</s3>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">10-0236313</idno>
<date when="2010">2010</date>
<idno type="stanalyst">PASCAL 10-0236313 INIST</idno>
<idno type="RBID">Pascal:10-0236313</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">002698</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Unsupervised Object Discovery: A Comparison</title>
<author><name sortKey="Tuytelaars, Tinne" sort="Tuytelaars, Tinne" uniqKey="Tuytelaars T" first="Tinne" last="Tuytelaars">Tinne Tuytelaars</name>
<affiliation><inist:fA14 i1="01"><s1>ESAT-PSI, K.U. Leuven, Kasteelpark Arenberg 10, bus 2241</s1>
<s2>Leuven 3001</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Lampert, Christoph H" sort="Lampert, Christoph H" uniqKey="Lampert C" first="Christoph H." last="Lampert">Christoph H. Lampert</name>
<affiliation><inist:fA14 i1="02"><s1>Max Planck Institute for Biological Cybernetics</s1>
<s2>Tübingen</s2>
<s3>DEU</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Blaschko, Matthew B" sort="Blaschko, Matthew B" uniqKey="Blaschko M" first="Matthew B." last="Blaschko">Matthew B. Blaschko</name>
<affiliation><inist:fA14 i1="02"><s1>Max Planck Institute for Biological Cybernetics</s1>
<s2>Tübingen</s2>
<s3>DEU</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="03"><s1>University of Oxford</s1>
<s2>Oxford</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Buntine, Wray" sort="Buntine, Wray" uniqKey="Buntine W" first="Wray" last="Buntine">Wray Buntine</name>
<affiliation><inist:fA14 i1="04"><s1>NICTA</s1>
<s2>Canberra</s2>
<s3>AUS</s3>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="05"><s1>Australian National University</s1>
<s2>Canberra</s2>
<s3>AUS</s3>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal of computer vision</title>
<title level="j" type="abbreviated">Int. j. comput. vis.</title>
<idno type="ISSN">0920-5691</idno>
<imprint><date when="2010">2010</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal of computer vision</title>
<title level="j" type="abbreviated">Int. j. comput. vis.</title>
<idno type="ISSN">0920-5691</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Cluster analysis</term>
<term>Computer vision</term>
<term>Image databank</term>
<term>Image processing</term>
<term>Latent variable model</term>
<term>Modeling</term>
<term>Object recognition</term>
<term>Spectral method</term>
<term>Unsupervised learning</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Traitement image</term>
<term>Banque image</term>
<term>Vision ordinateur</term>
<term>Modèle variable latente</term>
<term>Modélisation</term>
<term>Méthode spectrale</term>
<term>Analyse amas</term>
<term>.</term>
<term>Reconnaissance objet</term>
<term>Apprentissage non supervisé</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0920-5691</s0>
</fA01>
<fA03 i2="1"><s0>Int. j. comput. vis.</s0>
</fA03>
<fA05><s2>88</s2>
</fA05>
<fA06><s2>2</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Unsupervised Object Discovery: A Comparison</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>Probabilistic Models for Image Understanding</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>TUYTELAARS (Tinne)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>LAMPERT (Christoph H.)</s1>
</fA11>
<fA11 i1="03" i2="1"><s1>BLASCHKO (Matthew B.)</s1>
</fA11>
<fA11 i1="04" i2="1"><s1>BUNTINE (Wray)</s1>
</fA11>
<fA12 i1="01" i2="1"><s1>TRIGGS (Bill)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="02" i2="1"><s1>WILLIAMS (Christopher K. I.)</s1>
<s9>ed.</s9>
</fA12>
<fA14 i1="01"><s1>ESAT-PSI, K.U. Leuven, Kasteelpark Arenberg 10, bus 2241</s1>
<s2>Leuven 3001</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA14 i1="02"><s1>Max Planck Institute for Biological Cybernetics</s1>
<s2>Tübingen</s2>
<s3>DEU</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</fA14>
<fA14 i1="03"><s1>University of Oxford</s1>
<s2>Oxford</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
</fA14>
<fA14 i1="04"><s1>NICTA</s1>
<s2>Canberra</s2>
<s3>AUS</s3>
<sZ>4 aut.</sZ>
</fA14>
<fA14 i1="05"><s1>Australian National University</s1>
<s2>Canberra</s2>
<s3>AUS</s3>
<sZ>4 aut.</sZ>
</fA14>
<fA15 i1="01"><s1>Laboratoire Jean Kuntzman</s1>
<s2>Grenoble</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</fA15>
<fA15 i1="02"><s1>University of Edinburgh</s1>
<s2>Edinburgh</s2>
<s3>GBR</s3>
<sZ>2 aut.</sZ>
</fA15>
<fA20><s1>284-302</s1>
</fA20>
<fA21><s1>2010</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>21361</s2>
<s5>354000182008660070</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2010 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>3/4 p.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>10-0236313</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>International journal of computer vision</s0>
</fA64>
<fA66 i1="01"><s0>DEU</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02C03</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D02B07B</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Image processing</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Banque image</s0>
<s5>06</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Image databank</s0>
<s5>06</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Banco imagen</s0>
<s5>06</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Vision ordinateur</s0>
<s5>07</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Computer vision</s0>
<s5>07</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Visión ordenador</s0>
<s5>07</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Modèle variable latente</s0>
<s5>18</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Latent variable model</s0>
<s5>18</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Modelo variable latente</s0>
<s5>18</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Modélisation</s0>
<s5>23</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Modeling</s0>
<s5>23</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Modelización</s0>
<s5>23</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Méthode spectrale</s0>
<s5>24</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Spectral method</s0>
<s5>24</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Método espectral</s0>
<s5>24</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Analyse amas</s0>
<s5>25</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Cluster analysis</s0>
<s5>25</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Analisis cluster</s0>
<s5>25</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>.</s0>
<s4>INC</s4>
<s5>82</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Reconnaissance objet</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Object recognition</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Reconocimiento de objetos</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>Apprentissage non supervisé</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG"><s0>Unsupervised learning</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA"><s0>Aprendizaje no supervisado</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fN21><s1>158</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
</standard>
<server><NO>PASCAL 10-0236313 INIST</NO>
<ET>Unsupervised Object Discovery: A Comparison</ET>
<AU>TUYTELAARS (Tinne); LAMPERT (Christoph H.); BLASCHKO (Matthew B.); BUNTINE (Wray); TRIGGS (Bill); WILLIAMS (Christopher K. I.)</AU>
<AF>ESAT-PSI, K.U. Leuven, Kasteelpark Arenberg 10, bus 2241/Leuven 3001/Belgique (1 aut.); Max Planck Institute for Biological Cybernetics/Tübingen/Allemagne (2 aut., 3 aut.); University of Oxford/Oxford/Royaume-Uni (3 aut.); NICTA/Canberra/Australie (4 aut.); Australian National University/Canberra/Australie (4 aut.); Laboratoire Jean Kuntzman/Grenoble/France (1 aut.); University of Edinburgh/Edinburgh/Royaume-Uni (2 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>International journal of computer vision; ISSN 0920-5691; Allemagne; Da. 2010; Vol. 88; No. 2; Pp. 284-302; Bibl. 3/4 p.</SO>
<LA>Anglais</LA>
<EA>The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.</EA>
<CC>001D02C03; 001D02B07B</CC>
<FD>Traitement image; Banque image; Vision ordinateur; Modèle variable latente; Modélisation; Méthode spectrale; Analyse amas; .; Reconnaissance objet; Apprentissage non supervisé</FD>
<ED>Image processing; Image databank; Computer vision; Latent variable model; Modeling; Spectral method; Cluster analysis; Object recognition; Unsupervised learning</ED>
<SD>Procesamiento imagen; Banco imagen; Visión ordenador; Modelo variable latente; Modelización; Método espectral; Analisis cluster; Reconocimiento de objetos; Aprendizaje no supervisado</SD>
<LO>INIST-21361.354000182008660070</LO>
<ID>10-0236313</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/PascalFrancis/Corpus

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002698 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 002698 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Asie
   |area=    AustralieFrV1
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:10-0236313
   |texte=   Unsupervised Object Discovery: A Comparison
}}

This area was generated with Dilib version V0.6.33.
Data generation: Tue Dec 5 10:43:12 2017. Site generation: Tue Mar 5 14:07:20 2024

	Serveur d'exploration sur les relations entre la France et l'Australie
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur les relations entre la France et l'Australie

Unsupervised Object Discovery: A Comparison

Unsupervised Object Discovery: A Comparison

Source :

Descripteurs français

English descriptors

Abstract

Notice en format standard (ISO 2709)

Format Inist (serveur)

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri