Approximating morphological operators with part-based representations learned by asymmetric auto-encoders
This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want thi...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Blusseau Samy [verfasserIn] Ponchon Bastien [verfasserIn] Velasco-Forero Santiago [verfasserIn] Angulo Jesús [verfasserIn] Bloch Isabelle [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2020 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
In: Mathematical Morphology ; 4(2020), 1, Seite 64-86 volume:4 ; year:2020 ; number:1 ; pages:64-86 |
|---|
| Links: |
|---|
| DOI / URN: |
10.1515/mathm-2020-0102 |
|---|
| Katalog-ID: |
DOAJ066482283 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | DOAJ066482283 | ||
| 003 | DE-627 | ||
| 005 | 20230228051020.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230228s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1515/mathm-2020-0102 |2 doi | |
| 035 | |a (DE-627)DOAJ066482283 | ||
| 035 | |a (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 050 | 0 | |a QA1-939 | |
| 100 | 0 | |a Blusseau Samy |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. | ||
| 650 | 4 | |a non-negative sparse coding | |
| 650 | 4 | |a auto-encoders | |
| 650 | 4 | |a mathematical morphology | |
| 650 | 4 | |a morphological invariance | |
| 650 | 4 | |a representation learning | |
| 650 | 4 | |a xai | |
| 650 | 4 | |a 06-08 | |
| 650 | 4 | |a 15a23 | |
| 650 | 4 | |a 5a80 | |
| 650 | 4 | |a 68t07 | |
| 650 | 4 | |a 68t09 | |
| 650 | 4 | |a 68u10 | |
| 653 | 0 | |a Mathematics | |
| 700 | 0 | |a Ponchon Bastien |e verfasserin |4 aut | |
| 700 | 0 | |a Velasco-Forero Santiago |e verfasserin |4 aut | |
| 700 | 0 | |a Angulo Jesús |e verfasserin |4 aut | |
| 700 | 0 | |a Bloch Isabelle |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i In |t Mathematical Morphology |g 4(2020), 1, Seite 64-86 |
| 773 | 1 | 8 | |g volume:4 |g year:2020 |g number:1 |g pages:64-86 |
| 856 | 4 | 0 | |u https://doi.org/10.1515/mathm-2020-0102 |z kostenfrei |
| 856 | 4 | 0 | |u https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 |z kostenfrei |
| 856 | 4 | 0 | |u https://doi.org/10.1515/mathm-2020-0102 |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/2353-3390 |y Journal toc |z kostenfrei |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_DOAJ | ||
| 951 | |a AR | ||
| 952 | |d 4 |j 2020 |e 1 |h 64-86 | ||
| author_variant |
b s bs p b pb v f s vfs a j aj b i bi |
|---|---|
| matchkey_str |
blusseausamyponchonbastienvelascoforeros:2020----:prxmtnmrhlgclprtrwtprbsdersnainlan |
| hierarchy_sort_str |
2020 |
| callnumber-subject-code |
QA |
| publishDate |
2020 |
| allfields |
10.1515/mathm-2020-0102 doi (DE-627)DOAJ066482283 (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 DE-627 ger DE-627 rakwb eng QA1-939 Blusseau Samy verfasserin aut Approximating morphological operators with part-based representations learned by asymmetric auto-encoders 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 Mathematics Ponchon Bastien verfasserin aut Velasco-Forero Santiago verfasserin aut Angulo Jesús verfasserin aut Bloch Isabelle verfasserin aut In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 kostenfrei https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/toc/2353-3390 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 4 2020 1 64-86 |
| spelling |
10.1515/mathm-2020-0102 doi (DE-627)DOAJ066482283 (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 DE-627 ger DE-627 rakwb eng QA1-939 Blusseau Samy verfasserin aut Approximating morphological operators with part-based representations learned by asymmetric auto-encoders 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 Mathematics Ponchon Bastien verfasserin aut Velasco-Forero Santiago verfasserin aut Angulo Jesús verfasserin aut Bloch Isabelle verfasserin aut In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 kostenfrei https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/toc/2353-3390 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 4 2020 1 64-86 |
| allfields_unstemmed |
10.1515/mathm-2020-0102 doi (DE-627)DOAJ066482283 (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 DE-627 ger DE-627 rakwb eng QA1-939 Blusseau Samy verfasserin aut Approximating morphological operators with part-based representations learned by asymmetric auto-encoders 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 Mathematics Ponchon Bastien verfasserin aut Velasco-Forero Santiago verfasserin aut Angulo Jesús verfasserin aut Bloch Isabelle verfasserin aut In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 kostenfrei https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/toc/2353-3390 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 4 2020 1 64-86 |
| allfieldsGer |
10.1515/mathm-2020-0102 doi (DE-627)DOAJ066482283 (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 DE-627 ger DE-627 rakwb eng QA1-939 Blusseau Samy verfasserin aut Approximating morphological operators with part-based representations learned by asymmetric auto-encoders 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 Mathematics Ponchon Bastien verfasserin aut Velasco-Forero Santiago verfasserin aut Angulo Jesús verfasserin aut Bloch Isabelle verfasserin aut In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 kostenfrei https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/toc/2353-3390 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 4 2020 1 64-86 |
| allfieldsSound |
10.1515/mathm-2020-0102 doi (DE-627)DOAJ066482283 (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 DE-627 ger DE-627 rakwb eng QA1-939 Blusseau Samy verfasserin aut Approximating morphological operators with part-based representations learned by asymmetric auto-encoders 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 Mathematics Ponchon Bastien verfasserin aut Velasco-Forero Santiago verfasserin aut Angulo Jesús verfasserin aut Bloch Isabelle verfasserin aut In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 kostenfrei https://doi.org/10.1515/mathm-2020-0102 kostenfrei https://doaj.org/toc/2353-3390 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 4 2020 1 64-86 |
| language |
English |
| source |
In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 |
| sourceStr |
In Mathematical Morphology 4(2020), 1, Seite 64-86 volume:4 year:2020 number:1 pages:64-86 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 Mathematics |
| isfreeaccess_bool |
true |
| container_title |
Mathematical Morphology |
| authorswithroles_txt_mv |
Blusseau Samy @@aut@@ Ponchon Bastien @@aut@@ Velasco-Forero Santiago @@aut@@ Angulo Jesús @@aut@@ Bloch Isabelle @@aut@@ |
| publishDateDaySort_date |
2020-01-01T00:00:00Z |
| id |
DOAJ066482283 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ066482283</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230228051020.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230228s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1515/mathm-2020-0102</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ066482283</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA1-939</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Blusseau Samy</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Approximating morphological operators with part-based representations learned by asymmetric auto-encoders</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">non-negative sparse coding</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">auto-encoders</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">mathematical morphology</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">morphological invariance</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">representation learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">xai</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">06-08</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">15a23</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">5a80</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">68t07</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">68t09</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">68u10</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Mathematics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ponchon Bastien</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Velasco-Forero Santiago</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Angulo Jesús</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Bloch Isabelle</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Mathematical Morphology</subfield><subfield code="g">4(2020), 1, Seite 64-86</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:4</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:64-86</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1515/mathm-2020-0102</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1515/mathm-2020-0102</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2353-3390</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">4</subfield><subfield code="j">2020</subfield><subfield code="e">1</subfield><subfield code="h">64-86</subfield></datafield></record></collection>
|
| callnumber-first |
Q - Science |
| author |
Blusseau Samy |
| spellingShingle |
Blusseau Samy misc QA1-939 misc non-negative sparse coding misc auto-encoders misc mathematical morphology misc morphological invariance misc representation learning misc xai misc 06-08 misc 15a23 misc 5a80 misc 68t07 misc 68t09 misc 68u10 misc Mathematics Approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| authorStr |
Blusseau Samy |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut |
| collection |
DOAJ |
| remote_str |
true |
| callnumber-label |
QA1-939 |
| illustrated |
Not Illustrated |
| topic_title |
QA1-939 Approximating morphological operators with part-based representations learned by asymmetric auto-encoders non-negative sparse coding auto-encoders mathematical morphology morphological invariance representation learning xai 06-08 15a23 5a80 68t07 68t09 68u10 |
| topic |
misc QA1-939 misc non-negative sparse coding misc auto-encoders misc mathematical morphology misc morphological invariance misc representation learning misc xai misc 06-08 misc 15a23 misc 5a80 misc 68t07 misc 68t09 misc 68u10 misc Mathematics |
| topic_unstemmed |
misc QA1-939 misc non-negative sparse coding misc auto-encoders misc mathematical morphology misc morphological invariance misc representation learning misc xai misc 06-08 misc 15a23 misc 5a80 misc 68t07 misc 68t09 misc 68u10 misc Mathematics |
| topic_browse |
misc QA1-939 misc non-negative sparse coding misc auto-encoders misc mathematical morphology misc morphological invariance misc representation learning misc xai misc 06-08 misc 15a23 misc 5a80 misc 68t07 misc 68t09 misc 68u10 misc Mathematics |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Mathematical Morphology |
| hierarchy_top_title |
Mathematical Morphology |
| isfreeaccess_txt |
true |
| title |
Approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| ctrlnum |
(DE-627)DOAJ066482283 (DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6 |
| title_full |
Approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| author_sort |
Blusseau Samy |
| journal |
Mathematical Morphology |
| journalStr |
Mathematical Morphology |
| callnumber-first-code |
Q |
| lang_code |
eng |
| isOA_bool |
true |
| recordtype |
marc |
| publishDateSort |
2020 |
| contenttype_str_mv |
txt |
| container_start_page |
64 |
| author_browse |
Blusseau Samy Ponchon Bastien Velasco-Forero Santiago Angulo Jesús Bloch Isabelle |
| container_volume |
4 |
| class |
QA1-939 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Blusseau Samy |
| doi_str_mv |
10.1515/mathm-2020-0102 |
| author2-role |
verfasserin |
| title_sort |
approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| callnumber |
QA1-939 |
| title_auth |
Approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| abstract |
This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. |
| abstractGer |
This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. |
| abstract_unstemmed |
This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ |
| container_issue |
1 |
| title_short |
Approximating morphological operators with part-based representations learned by asymmetric auto-encoders |
| url |
https://doi.org/10.1515/mathm-2020-0102 https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6 https://doaj.org/toc/2353-3390 |
| remote_bool |
true |
| author2 |
Ponchon Bastien Velasco-Forero Santiago Angulo Jesús Bloch Isabelle |
| author2Str |
Ponchon Bastien Velasco-Forero Santiago Angulo Jesús Bloch Isabelle |
| callnumber-subject |
QA - Mathematics |
| mediatype_str_mv |
c |
| isOA_txt |
true |
| hochschulschrift_bool |
false |
| doi_str |
10.1515/mathm-2020-0102 |
| callnumber-a |
QA1-939 |
| up_date |
2024-07-03T20:17:45.454Z |
| _version_ |
1803590424813633536 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ066482283</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230228051020.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230228s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1515/mathm-2020-0102</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ066482283</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ3c68d630cb474e60bdd8dac6784681a6</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA1-939</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Blusseau Samy</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Approximating morphological operators with part-based representations learned by asymmetric auto-encoders</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">non-negative sparse coding</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">auto-encoders</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">mathematical morphology</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">morphological invariance</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">representation learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">xai</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">06-08</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">15a23</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">5a80</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">68t07</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">68t09</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">68u10</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Mathematics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ponchon Bastien</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Velasco-Forero Santiago</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Angulo Jesús</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Bloch Isabelle</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Mathematical Morphology</subfield><subfield code="g">4(2020), 1, Seite 64-86</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:4</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:64-86</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1515/mathm-2020-0102</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/3c68d630cb474e60bdd8dac6784681a6</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1515/mathm-2020-0102</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2353-3390</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">4</subfield><subfield code="j">2020</subfield><subfield code="e">1</subfield><subfield code="h">64-86</subfield></datafield></record></collection>
|
| score |
7.4007654 |