PFNet: a novel part fusion network for fine-grained visual categorization
Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this pape...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Liang, Jingyun [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2018 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Springer Science+Business Media, LLC, part of Springer Nature 2018 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Multimedia tools and applications - Springer US, 1995, 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 |
|---|---|
| Übergeordnetes Werk: |
volume:79 ; year:2018 ; number:45-46 ; day:15 ; month:12 ; pages:33397-33416 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11042-018-7047-5 |
|---|
| Katalog-ID: |
OLC2121595112 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2121595112 | ||
| 003 | DE-627 | ||
| 005 | 20230504185021.0 | ||
| 007 | tu | ||
| 008 | 230504s2018 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11042-018-7047-5 |2 doi | |
| 035 | |a (DE-627)OLC2121595112 | ||
| 035 | |a (DE-He213)s11042-018-7047-5-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 Liang, Jingyun |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a PFNet: a novel part fusion network for fine-grained visual categorization |
| 264 | 1 | |c 2018 | |
| 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, LLC, part of Springer Nature 2018 | ||
| 520 | |a Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. | ||
| 650 | 4 | |a Fine-grained visual categorization | |
| 650 | 4 | |a Image classification | |
| 650 | 4 | |a Convolutional neural network | |
| 700 | 1 | |a Guo, Jinlin |4 aut | |
| 700 | 1 | |a Guo, Yanming |4 aut | |
| 700 | 1 | |a Lao, Songyang |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Multimedia tools and applications |d Springer US, 1995 |g 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 |w (DE-627)189064145 |w (DE-600)1287642-2 |w (DE-576)052842126 |x 1380-7501 |7 nnns |
| 773 | 1 | 8 | |g volume:79 |g year:2018 |g number:45-46 |g day:15 |g month:12 |g pages:33397-33416 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11042-018-7047-5 |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 79 |j 2018 |e 45-46 |b 15 |c 12 |h 33397-33416 | ||
| author_variant |
j l jl j g jg y g yg s l sl |
|---|---|
| matchkey_str |
article:13807501:2018----::feaoeprfsontokofngandi |
| hierarchy_sort_str |
2018 |
| publishDate |
2018 |
| allfields |
10.1007/s11042-018-7047-5 doi (DE-627)OLC2121595112 (DE-He213)s11042-018-7047-5-p DE-627 ger DE-627 rakwb eng 070 004 VZ Liang, Jingyun verfasserin aut PFNet: a novel part fusion network for fine-grained visual categorization 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. Fine-grained visual categorization Image classification Convolutional neural network Guo, Jinlin aut Guo, Yanming aut Lao, Songyang aut Enthalten in Multimedia tools and applications Springer US, 1995 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 https://doi.org/10.1007/s11042-018-7047-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 79 2018 45-46 15 12 33397-33416 |
| spelling |
10.1007/s11042-018-7047-5 doi (DE-627)OLC2121595112 (DE-He213)s11042-018-7047-5-p DE-627 ger DE-627 rakwb eng 070 004 VZ Liang, Jingyun verfasserin aut PFNet: a novel part fusion network for fine-grained visual categorization 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. Fine-grained visual categorization Image classification Convolutional neural network Guo, Jinlin aut Guo, Yanming aut Lao, Songyang aut Enthalten in Multimedia tools and applications Springer US, 1995 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 https://doi.org/10.1007/s11042-018-7047-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 79 2018 45-46 15 12 33397-33416 |
| allfields_unstemmed |
10.1007/s11042-018-7047-5 doi (DE-627)OLC2121595112 (DE-He213)s11042-018-7047-5-p DE-627 ger DE-627 rakwb eng 070 004 VZ Liang, Jingyun verfasserin aut PFNet: a novel part fusion network for fine-grained visual categorization 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. Fine-grained visual categorization Image classification Convolutional neural network Guo, Jinlin aut Guo, Yanming aut Lao, Songyang aut Enthalten in Multimedia tools and applications Springer US, 1995 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 https://doi.org/10.1007/s11042-018-7047-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 79 2018 45-46 15 12 33397-33416 |
| allfieldsGer |
10.1007/s11042-018-7047-5 doi (DE-627)OLC2121595112 (DE-He213)s11042-018-7047-5-p DE-627 ger DE-627 rakwb eng 070 004 VZ Liang, Jingyun verfasserin aut PFNet: a novel part fusion network for fine-grained visual categorization 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. Fine-grained visual categorization Image classification Convolutional neural network Guo, Jinlin aut Guo, Yanming aut Lao, Songyang aut Enthalten in Multimedia tools and applications Springer US, 1995 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 https://doi.org/10.1007/s11042-018-7047-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 79 2018 45-46 15 12 33397-33416 |
| allfieldsSound |
10.1007/s11042-018-7047-5 doi (DE-627)OLC2121595112 (DE-He213)s11042-018-7047-5-p DE-627 ger DE-627 rakwb eng 070 004 VZ Liang, Jingyun verfasserin aut PFNet: a novel part fusion network for fine-grained visual categorization 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. Fine-grained visual categorization Image classification Convolutional neural network Guo, Jinlin aut Guo, Yanming aut Lao, Songyang aut Enthalten in Multimedia tools and applications Springer US, 1995 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 https://doi.org/10.1007/s11042-018-7047-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 AR 79 2018 45-46 15 12 33397-33416 |
| language |
English |
| source |
Enthalten in Multimedia tools and applications 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 |
| sourceStr |
Enthalten in Multimedia tools and applications 79(2018), 45-46 vom: 15. Dez., Seite 33397-33416 volume:79 year:2018 number:45-46 day:15 month:12 pages:33397-33416 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Fine-grained visual categorization Image classification Convolutional neural network |
| dewey-raw |
070 |
| isfreeaccess_bool |
false |
| container_title |
Multimedia tools and applications |
| authorswithroles_txt_mv |
Liang, Jingyun @@aut@@ Guo, Jinlin @@aut@@ Guo, Yanming @@aut@@ Lao, Songyang @@aut@@ |
| publishDateDaySort_date |
2018-12-15T00:00:00Z |
| hierarchy_top_id |
189064145 |
| dewey-sort |
270 |
| id |
OLC2121595112 |
| 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">OLC2121595112</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230504185021.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230504s2018 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11042-018-7047-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2121595112</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11042-018-7047-5-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">Liang, Jingyun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">PFNet: a novel part fusion network for fine-grained visual categorization</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2018</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, LLC, part of Springer Nature 2018</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fine-grained visual categorization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Jinlin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Yanming</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lao, Songyang</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">79(2018), 45-46 vom: 15. Dez., Seite 33397-33416</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:79</subfield><subfield code="g">year:2018</subfield><subfield code="g">number:45-46</subfield><subfield code="g">day:15</subfield><subfield code="g">month:12</subfield><subfield code="g">pages:33397-33416</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11042-018-7047-5</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">79</subfield><subfield code="j">2018</subfield><subfield code="e">45-46</subfield><subfield code="b">15</subfield><subfield code="c">12</subfield><subfield code="h">33397-33416</subfield></datafield></record></collection>
|
| author |
Liang, Jingyun |
| spellingShingle |
Liang, Jingyun ddc 070 misc Fine-grained visual categorization misc Image classification misc Convolutional neural network PFNet: a novel part fusion network for fine-grained visual categorization |
| authorStr |
Liang, Jingyun |
| 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 aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1380-7501 |
| topic_title |
070 004 VZ PFNet: a novel part fusion network for fine-grained visual categorization Fine-grained visual categorization Image classification Convolutional neural network |
| topic |
ddc 070 misc Fine-grained visual categorization misc Image classification misc Convolutional neural network |
| topic_unstemmed |
ddc 070 misc Fine-grained visual categorization misc Image classification misc Convolutional neural network |
| topic_browse |
ddc 070 misc Fine-grained visual categorization misc Image classification misc Convolutional neural network |
| 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 |
PFNet: a novel part fusion network for fine-grained visual categorization |
| ctrlnum |
(DE-627)OLC2121595112 (DE-He213)s11042-018-7047-5-p |
| title_full |
PFNet: a novel part fusion network for fine-grained visual categorization |
| author_sort |
Liang, Jingyun |
| 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 |
2018 |
| contenttype_str_mv |
txt |
| container_start_page |
33397 |
| author_browse |
Liang, Jingyun Guo, Jinlin Guo, Yanming Lao, Songyang |
| container_volume |
79 |
| class |
070 004 VZ |
| format_se |
Aufsätze |
| author-letter |
Liang, Jingyun |
| doi_str_mv |
10.1007/s11042-018-7047-5 |
| dewey-full |
070 004 |
| title_sort |
pfnet: a novel part fusion network for fine-grained visual categorization |
| title_auth |
PFNet: a novel part fusion network for fine-grained visual categorization |
| abstract |
Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. © Springer Science+Business Media, LLC, part of Springer Nature 2018 |
| abstractGer |
Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. © Springer Science+Business Media, LLC, part of Springer Nature 2018 |
| abstract_unstemmed |
Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC. © Springer Science+Business Media, LLC, part of Springer Nature 2018 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW GBV_ILN_70 |
| container_issue |
45-46 |
| title_short |
PFNet: a novel part fusion network for fine-grained visual categorization |
| url |
https://doi.org/10.1007/s11042-018-7047-5 |
| remote_bool |
false |
| author2 |
Guo, Jinlin Guo, Yanming Lao, Songyang |
| author2Str |
Guo, Jinlin Guo, Yanming Lao, Songyang |
| ppnlink |
189064145 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11042-018-7047-5 |
| up_date |
2024-07-04T07:29:02.348Z |
| _version_ |
1803632658188599296 |
| 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">OLC2121595112</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230504185021.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230504s2018 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11042-018-7047-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2121595112</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11042-018-7047-5-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">Liang, Jingyun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">PFNet: a novel part fusion network for fine-grained visual categorization</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2018</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, LLC, part of Springer Nature 2018</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract The existing methods in fine-grained visual categorization focus on integrating multiple deep CNN models or complicated attention mechanism, resulting in increasing cumbersome networks. In addition, most methods rely on part annotations which requires expensive expert guidance. In this paper, without extra annotation, we propose a novel part fusion network (PFNet) to effectively fuse discriminative image parts for classification. More specifically, PFNet consists of a part feature extractor to extract part features and a two-level classification network to utilize part-level and image-level features simultaneously. Part-level features are trained with the weighted part loss, which embeds a weighting mechanism based on different parts’ characteristics. Easy parts, hard parts and background parts are proposed and discriminatively used for classification. Moreover, part-level features are fused to form an image-level feature so as to introduce global supervision and generate final predictions. Experiments on three popular benchmark datasets show that our framework achieves competitive performance compared with the state-of-the-art. Code is available at https://github.com/MichaelLiang12/PFNet-FGVC.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fine-grained visual categorization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Jinlin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Yanming</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lao, Songyang</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">79(2018), 45-46 vom: 15. Dez., Seite 33397-33416</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:79</subfield><subfield code="g">year:2018</subfield><subfield code="g">number:45-46</subfield><subfield code="g">day:15</subfield><subfield code="g">month:12</subfield><subfield code="g">pages:33397-33416</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11042-018-7047-5</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">79</subfield><subfield code="j">2018</subfield><subfield code="e">45-46</subfield><subfield code="b">15</subfield><subfield code="c">12</subfield><subfield code="h">33397-33416</subfield></datafield></record></collection>
|
| score |
7.4012823 |