Large scale classifiers for visual classification tasks
Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resou...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Doan, Thanh-Nghi [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2014 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Springer Science+Business Media New York 2014 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Multimedia tools and applications - Springer US, 1995, 74(2014), 4 vom: 13. Juni, Seite 1199-1224 |
|---|---|
| Übergeordnetes Werk: |
volume:74 ; year:2014 ; number:4 ; day:13 ; month:06 ; pages:1199-1224 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11042-014-2049-4 |
|---|
| Katalog-ID: |
OLC2035014786 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2035014786 | ||
| 003 | DE-627 | ||
| 005 | 20230503192818.0 | ||
| 007 | tu | ||
| 008 | 200819s2014 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11042-014-2049-4 |2 doi | |
| 035 | |a (DE-627)OLC2035014786 | ||
| 035 | |a (DE-He213)s11042-014-2049-4-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 070 |a 004 |q VZ |
| 100 | 1 | |a Doan, Thanh-Nghi |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Large scale classifiers for visual classification tasks |
| 264 | 1 | |c 2014 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © Springer Science+Business Media New York 2014 | ||
| 520 | |a Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. | ||
| 650 | 4 | |a Large scale visual classification | |
| 650 | 4 | |a Support vector machines | |
| 650 | 4 | |a Incremental learning method | |
| 650 | 4 | |a Balanced bagging | |
| 650 | 4 | |a High performance computing | |
| 700 | 1 | |a Do, Thanh-Nghi |4 aut | |
| 700 | 1 | |a Poulet, François |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Multimedia tools and applications |d Springer US, 1995 |g 74(2014), 4 vom: 13. Juni, Seite 1199-1224 |w (DE-627)189064145 |w (DE-600)1287642-2 |w (DE-576)052842126 |x 1380-7501 |7 nnns |
| 773 | 1 | 8 | |g volume:74 |g year:2014 |g number:4 |g day:13 |g month:06 |g pages:1199-1224 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11042-014-2049-4 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a SSG-OLC-BUB | ||
| 912 | |a SSG-OLC-MKW | ||
| 912 | |a GBV_ILN_70 | ||
| 951 | |a AR | ||
| 952 | |d 74 |j 2014 |e 4 |b 13 |c 06 |h 1199-1224 | ||
| author_variant |
t n d tnd t n d tnd f p fp |
|---|---|
| matchkey_str |
article:13807501:2014----::agsaelsiirfriullsi |
| hierarchy_sort_str |
2014 |
| publishDate |
2014 |
| allfields |
10.1007/s11042-014-2049-4 doi (DE-627)OLC2035014786 (DE-He213)s11042-014-2049-4-p DE-627 ger DE-627 rakwb eng 070 004 VZ Doan, Thanh-Nghi verfasserin aut Large scale classifiers for visual classification tasks 2014 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media New York 2014 Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing Do, Thanh-Nghi aut Poulet, François aut Enthalten in Multimedia tools and applications Springer US, 1995 74(2014), 4 vom: 13. Juni, Seite 1199-1224 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 https://doi.org/10.1007/s11042-014-2049-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 74 2014 4 13 06 1199-1224 |
| spelling |
10.1007/s11042-014-2049-4 doi (DE-627)OLC2035014786 (DE-He213)s11042-014-2049-4-p DE-627 ger DE-627 rakwb eng 070 004 VZ Doan, Thanh-Nghi verfasserin aut Large scale classifiers for visual classification tasks 2014 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media New York 2014 Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing Do, Thanh-Nghi aut Poulet, François aut Enthalten in Multimedia tools and applications Springer US, 1995 74(2014), 4 vom: 13. Juni, Seite 1199-1224 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 https://doi.org/10.1007/s11042-014-2049-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 74 2014 4 13 06 1199-1224 |
| allfields_unstemmed |
10.1007/s11042-014-2049-4 doi (DE-627)OLC2035014786 (DE-He213)s11042-014-2049-4-p DE-627 ger DE-627 rakwb eng 070 004 VZ Doan, Thanh-Nghi verfasserin aut Large scale classifiers for visual classification tasks 2014 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media New York 2014 Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing Do, Thanh-Nghi aut Poulet, François aut Enthalten in Multimedia tools and applications Springer US, 1995 74(2014), 4 vom: 13. Juni, Seite 1199-1224 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 https://doi.org/10.1007/s11042-014-2049-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 74 2014 4 13 06 1199-1224 |
| allfieldsGer |
10.1007/s11042-014-2049-4 doi (DE-627)OLC2035014786 (DE-He213)s11042-014-2049-4-p DE-627 ger DE-627 rakwb eng 070 004 VZ Doan, Thanh-Nghi verfasserin aut Large scale classifiers for visual classification tasks 2014 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media New York 2014 Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing Do, Thanh-Nghi aut Poulet, François aut Enthalten in Multimedia tools and applications Springer US, 1995 74(2014), 4 vom: 13. Juni, Seite 1199-1224 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 https://doi.org/10.1007/s11042-014-2049-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 74 2014 4 13 06 1199-1224 |
| allfieldsSound |
10.1007/s11042-014-2049-4 doi (DE-627)OLC2035014786 (DE-He213)s11042-014-2049-4-p DE-627 ger DE-627 rakwb eng 070 004 VZ Doan, Thanh-Nghi verfasserin aut Large scale classifiers for visual classification tasks 2014 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media New York 2014 Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing Do, Thanh-Nghi aut Poulet, François aut Enthalten in Multimedia tools and applications Springer US, 1995 74(2014), 4 vom: 13. Juni, Seite 1199-1224 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 https://doi.org/10.1007/s11042-014-2049-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 74 2014 4 13 06 1199-1224 |
| language |
English |
| source |
Enthalten in Multimedia tools and applications 74(2014), 4 vom: 13. Juni, Seite 1199-1224 volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 |
| sourceStr |
Enthalten in Multimedia tools and applications 74(2014), 4 vom: 13. Juni, Seite 1199-1224 volume:74 year:2014 number:4 day:13 month:06 pages:1199-1224 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing |
| dewey-raw |
070 |
| isfreeaccess_bool |
false |
| container_title |
Multimedia tools and applications |
| authorswithroles_txt_mv |
Doan, Thanh-Nghi @@aut@@ Do, Thanh-Nghi @@aut@@ Poulet, François @@aut@@ |
| publishDateDaySort_date |
2014-06-13T00:00:00Z |
| hierarchy_top_id |
189064145 |
| dewey-sort |
270 |
| id |
OLC2035014786 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2035014786</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230503192818.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200819s2014 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11042-014-2049-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2035014786</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11042-014-2049-4-p</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="082" ind1="0" ind2="4"><subfield code="a">070</subfield><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Doan, Thanh-Nghi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Large scale classifiers for visual classification tasks</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2014</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">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Springer Science+Business Media New York 2014</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Large scale visual classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Support vector machines</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Incremental learning method</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Balanced bagging</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">High performance computing</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Do, Thanh-Nghi</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Poulet, François</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Multimedia tools and applications</subfield><subfield code="d">Springer US, 1995</subfield><subfield code="g">74(2014), 4 vom: 13. Juni, Seite 1199-1224</subfield><subfield code="w">(DE-627)189064145</subfield><subfield code="w">(DE-600)1287642-2</subfield><subfield code="w">(DE-576)052842126</subfield><subfield code="x">1380-7501</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:74</subfield><subfield code="g">year:2014</subfield><subfield code="g">number:4</subfield><subfield code="g">day:13</subfield><subfield code="g">month:06</subfield><subfield code="g">pages:1199-1224</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11042-014-2049-4</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</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_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-BUB</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MKW</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">74</subfield><subfield code="j">2014</subfield><subfield code="e">4</subfield><subfield code="b">13</subfield><subfield code="c">06</subfield><subfield code="h">1199-1224</subfield></datafield></record></collection>
|
| author |
Doan, Thanh-Nghi |
| spellingShingle |
Doan, Thanh-Nghi ddc 070 misc Large scale visual classification misc Support vector machines misc Incremental learning method misc Balanced bagging misc High performance computing Large scale classifiers for visual classification tasks |
| authorStr |
Doan, Thanh-Nghi |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)189064145 |
| format |
Article |
| dewey-ones |
070 - News media, journalism & publishing 004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1380-7501 |
| topic_title |
070 004 VZ Large scale classifiers for visual classification tasks Large scale visual classification Support vector machines Incremental learning method Balanced bagging High performance computing |
| topic |
ddc 070 misc Large scale visual classification misc Support vector machines misc Incremental learning method misc Balanced bagging misc High performance computing |
| topic_unstemmed |
ddc 070 misc Large scale visual classification misc Support vector machines misc Incremental learning method misc Balanced bagging misc High performance computing |
| topic_browse |
ddc 070 misc Large scale visual classification misc Support vector machines misc Incremental learning method misc Balanced bagging misc High performance computing |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Multimedia tools and applications |
| hierarchy_parent_id |
189064145 |
| dewey-tens |
070 - News media, journalism & publishing 000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Multimedia tools and applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 |
| title |
Large scale classifiers for visual classification tasks |
| ctrlnum |
(DE-627)OLC2035014786 (DE-He213)s11042-014-2049-4-p |
| title_full |
Large scale classifiers for visual classification tasks |
| author_sort |
Doan, Thanh-Nghi |
| journal |
Multimedia tools and applications |
| journalStr |
Multimedia tools and applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2014 |
| contenttype_str_mv |
txt |
| container_start_page |
1199 |
| author_browse |
Doan, Thanh-Nghi Do, Thanh-Nghi Poulet, François |
| container_volume |
74 |
| class |
070 004 VZ |
| format_se |
Aufsätze |
| author-letter |
Doan, Thanh-Nghi |
| doi_str_mv |
10.1007/s11042-014-2049-4 |
| dewey-full |
070 004 |
| title_sort |
large scale classifiers for visual classification tasks |
| title_auth |
Large scale classifiers for visual classification tasks |
| abstract |
Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. © Springer Science+Business Media New York 2014 |
| abstractGer |
Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. © Springer Science+Business Media New York 2014 |
| abstract_unstemmed |
Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM. © Springer Science+Business Media New York 2014 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 |
| container_issue |
4 |
| title_short |
Large scale classifiers for visual classification tasks |
| url |
https://doi.org/10.1007/s11042-014-2049-4 |
| remote_bool |
false |
| author2 |
Do, Thanh-Nghi Poulet, François |
| author2Str |
Do, Thanh-Nghi Poulet, François |
| ppnlink |
189064145 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11042-014-2049-4 |
| up_date |
2024-07-03T23:26:35.680Z |
| _version_ |
1803602305414594560 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2035014786</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230503192818.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200819s2014 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11042-014-2049-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2035014786</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11042-014-2049-4-p</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="082" ind1="0" ind2="4"><subfield code="a">070</subfield><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Doan, Thanh-Nghi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Large scale classifiers for visual classification tasks</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2014</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">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Springer Science+Business Media New York 2014</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Large scale visual classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Support vector machines</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Incremental learning method</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Balanced bagging</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">High performance computing</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Do, Thanh-Nghi</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Poulet, François</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Multimedia tools and applications</subfield><subfield code="d">Springer US, 1995</subfield><subfield code="g">74(2014), 4 vom: 13. Juni, Seite 1199-1224</subfield><subfield code="w">(DE-627)189064145</subfield><subfield code="w">(DE-600)1287642-2</subfield><subfield code="w">(DE-576)052842126</subfield><subfield code="x">1380-7501</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:74</subfield><subfield code="g">year:2014</subfield><subfield code="g">number:4</subfield><subfield code="g">day:13</subfield><subfield code="g">month:06</subfield><subfield code="g">pages:1199-1224</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11042-014-2049-4</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</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_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-BUB</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MKW</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">74</subfield><subfield code="j">2014</subfield><subfield code="e">4</subfield><subfield code="b">13</subfield><subfield code="c">06</subfield><subfield code="h">1199-1224</subfield></datafield></record></collection>
|
| score |
7.400708 |