Pairwise Generalization Network for Cross-Domain Image Recognition
Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain ima...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Liu, Y. B. [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2019 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Springer Science+Business Media, LLC, part of Springer Nature 2019 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Neural processing letters - Springer US, 1994, 52(2019), 2 vom: 16. Apr., Seite 1023-1041 |
|---|---|
| Übergeordnetes Werk: |
volume:52 ; year:2019 ; number:2 ; day:16 ; month:04 ; pages:1023-1041 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11063-019-10041-9 |
|---|
| Katalog-ID: |
OLC2119715149 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2119715149 | ||
| 003 | DE-627 | ||
| 005 | 20230504171722.0 | ||
| 007 | tu | ||
| 008 | 230504s2019 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11063-019-10041-9 |2 doi | |
| 035 | |a (DE-627)OLC2119715149 | ||
| 035 | |a (DE-He213)s11063-019-10041-9-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 000 |q VZ |
| 100 | 1 | |a Liu, Y. B. |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Pairwise Generalization Network for Cross-Domain Image Recognition |
| 264 | 1 | |c 2019 | |
| 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 2019 | ||
| 520 | |a Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. | ||
| 650 | 4 | |a Cross-domain | |
| 650 | 4 | |a Image recognition | |
| 650 | 4 | |a Pairwise | |
| 700 | 1 | |a Han, T. T. |4 aut | |
| 700 | 1 | |a Gao, Z. |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Neural processing letters |d Springer US, 1994 |g 52(2019), 2 vom: 16. Apr., Seite 1023-1041 |w (DE-627)198692617 |w (DE-600)1316823-X |w (DE-576)052842762 |x 1370-4621 |7 nnns |
| 773 | 1 | 8 | |g volume:52 |g year:2019 |g number:2 |g day:16 |g month:04 |g pages:1023-1041 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11063-019-10041-9 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-PSY | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_70 | ||
| 951 | |a AR | ||
| 952 | |d 52 |j 2019 |e 2 |b 16 |c 04 |h 1023-1041 | ||
| author_variant |
y b l yb ybl t t h tt tth z g zg |
|---|---|
| matchkey_str |
article:13704621:2019----::arieeeaiainewrfrrsdmi |
| hierarchy_sort_str |
2019 |
| publishDate |
2019 |
| allfields |
10.1007/s11063-019-10041-9 doi (DE-627)OLC2119715149 (DE-He213)s11063-019-10041-9-p DE-627 ger DE-627 rakwb eng 000 VZ Liu, Y. B. verfasserin aut Pairwise Generalization Network for Cross-Domain Image Recognition 2019 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. Cross-domain Image recognition Pairwise Han, T. T. aut Gao, Z. aut Enthalten in Neural processing letters Springer US, 1994 52(2019), 2 vom: 16. Apr., Seite 1023-1041 (DE-627)198692617 (DE-600)1316823-X (DE-576)052842762 1370-4621 nnns volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 https://doi.org/10.1007/s11063-019-10041-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-PSY SSG-OLC-MAT GBV_ILN_70 AR 52 2019 2 16 04 1023-1041 |
| spelling |
10.1007/s11063-019-10041-9 doi (DE-627)OLC2119715149 (DE-He213)s11063-019-10041-9-p DE-627 ger DE-627 rakwb eng 000 VZ Liu, Y. B. verfasserin aut Pairwise Generalization Network for Cross-Domain Image Recognition 2019 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. Cross-domain Image recognition Pairwise Han, T. T. aut Gao, Z. aut Enthalten in Neural processing letters Springer US, 1994 52(2019), 2 vom: 16. Apr., Seite 1023-1041 (DE-627)198692617 (DE-600)1316823-X (DE-576)052842762 1370-4621 nnns volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 https://doi.org/10.1007/s11063-019-10041-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-PSY SSG-OLC-MAT GBV_ILN_70 AR 52 2019 2 16 04 1023-1041 |
| allfields_unstemmed |
10.1007/s11063-019-10041-9 doi (DE-627)OLC2119715149 (DE-He213)s11063-019-10041-9-p DE-627 ger DE-627 rakwb eng 000 VZ Liu, Y. B. verfasserin aut Pairwise Generalization Network for Cross-Domain Image Recognition 2019 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. Cross-domain Image recognition Pairwise Han, T. T. aut Gao, Z. aut Enthalten in Neural processing letters Springer US, 1994 52(2019), 2 vom: 16. Apr., Seite 1023-1041 (DE-627)198692617 (DE-600)1316823-X (DE-576)052842762 1370-4621 nnns volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 https://doi.org/10.1007/s11063-019-10041-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-PSY SSG-OLC-MAT GBV_ILN_70 AR 52 2019 2 16 04 1023-1041 |
| allfieldsGer |
10.1007/s11063-019-10041-9 doi (DE-627)OLC2119715149 (DE-He213)s11063-019-10041-9-p DE-627 ger DE-627 rakwb eng 000 VZ Liu, Y. B. verfasserin aut Pairwise Generalization Network for Cross-Domain Image Recognition 2019 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. Cross-domain Image recognition Pairwise Han, T. T. aut Gao, Z. aut Enthalten in Neural processing letters Springer US, 1994 52(2019), 2 vom: 16. Apr., Seite 1023-1041 (DE-627)198692617 (DE-600)1316823-X (DE-576)052842762 1370-4621 nnns volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 https://doi.org/10.1007/s11063-019-10041-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-PSY SSG-OLC-MAT GBV_ILN_70 AR 52 2019 2 16 04 1023-1041 |
| allfieldsSound |
10.1007/s11063-019-10041-9 doi (DE-627)OLC2119715149 (DE-He213)s11063-019-10041-9-p DE-627 ger DE-627 rakwb eng 000 VZ Liu, Y. B. verfasserin aut Pairwise Generalization Network for Cross-Domain Image Recognition 2019 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. Cross-domain Image recognition Pairwise Han, T. T. aut Gao, Z. aut Enthalten in Neural processing letters Springer US, 1994 52(2019), 2 vom: 16. Apr., Seite 1023-1041 (DE-627)198692617 (DE-600)1316823-X (DE-576)052842762 1370-4621 nnns volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 https://doi.org/10.1007/s11063-019-10041-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-PSY SSG-OLC-MAT GBV_ILN_70 AR 52 2019 2 16 04 1023-1041 |
| language |
English |
| source |
Enthalten in Neural processing letters 52(2019), 2 vom: 16. Apr., Seite 1023-1041 volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 |
| sourceStr |
Enthalten in Neural processing letters 52(2019), 2 vom: 16. Apr., Seite 1023-1041 volume:52 year:2019 number:2 day:16 month:04 pages:1023-1041 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Cross-domain Image recognition Pairwise |
| dewey-raw |
000 |
| isfreeaccess_bool |
false |
| container_title |
Neural processing letters |
| authorswithroles_txt_mv |
Liu, Y. B. @@aut@@ Han, T. T. @@aut@@ Gao, Z. @@aut@@ |
| publishDateDaySort_date |
2019-04-16T00:00:00Z |
| hierarchy_top_id |
198692617 |
| dewey-sort |
0 |
| id |
OLC2119715149 |
| 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">OLC2119715149</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230504171722.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230504s2019 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11063-019-10041-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2119715149</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11063-019-10041-9-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">000</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Liu, Y. B.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Pairwise Generalization Network for Cross-Domain Image Recognition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</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 2019</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-domain</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pairwise</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, T. T.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gao, Z.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural processing letters</subfield><subfield code="d">Springer US, 1994</subfield><subfield code="g">52(2019), 2 vom: 16. Apr., Seite 1023-1041</subfield><subfield code="w">(DE-627)198692617</subfield><subfield code="w">(DE-600)1316823-X</subfield><subfield code="w">(DE-576)052842762</subfield><subfield code="x">1370-4621</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:52</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:2</subfield><subfield code="g">day:16</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:1023-1041</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11063-019-10041-9</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-PSY</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</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">52</subfield><subfield code="j">2019</subfield><subfield code="e">2</subfield><subfield code="b">16</subfield><subfield code="c">04</subfield><subfield code="h">1023-1041</subfield></datafield></record></collection>
|
| author |
Liu, Y. B. |
| spellingShingle |
Liu, Y. B. ddc 000 misc Cross-domain misc Image recognition misc Pairwise Pairwise Generalization Network for Cross-Domain Image Recognition |
| authorStr |
Liu, Y. B. |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)198692617 |
| format |
Article |
| dewey-ones |
000 - Computer science, information & general works |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1370-4621 |
| topic_title |
000 VZ Pairwise Generalization Network for Cross-Domain Image Recognition Cross-domain Image recognition Pairwise |
| topic |
ddc 000 misc Cross-domain misc Image recognition misc Pairwise |
| topic_unstemmed |
ddc 000 misc Cross-domain misc Image recognition misc Pairwise |
| topic_browse |
ddc 000 misc Cross-domain misc Image recognition misc Pairwise |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Neural processing letters |
| hierarchy_parent_id |
198692617 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Neural processing letters |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)198692617 (DE-600)1316823-X (DE-576)052842762 |
| title |
Pairwise Generalization Network for Cross-Domain Image Recognition |
| ctrlnum |
(DE-627)OLC2119715149 (DE-He213)s11063-019-10041-9-p |
| title_full |
Pairwise Generalization Network for Cross-Domain Image Recognition |
| author_sort |
Liu, Y. B. |
| journal |
Neural processing letters |
| journalStr |
Neural processing letters |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2019 |
| contenttype_str_mv |
txt |
| container_start_page |
1023 |
| author_browse |
Liu, Y. B. Han, T. T. Gao, Z. |
| container_volume |
52 |
| class |
000 VZ |
| format_se |
Aufsätze |
| author-letter |
Liu, Y. B. |
| doi_str_mv |
10.1007/s11063-019-10041-9 |
| dewey-full |
000 |
| title_sort |
pairwise generalization network for cross-domain image recognition |
| title_auth |
Pairwise Generalization Network for Cross-Domain Image Recognition |
| abstract |
Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. © Springer Science+Business Media, LLC, part of Springer Nature 2019 |
| abstractGer |
Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. © Springer Science+Business Media, LLC, part of Springer Nature 2019 |
| abstract_unstemmed |
Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods. © Springer Science+Business Media, LLC, part of Springer Nature 2019 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-PSY SSG-OLC-MAT GBV_ILN_70 |
| container_issue |
2 |
| title_short |
Pairwise Generalization Network for Cross-Domain Image Recognition |
| url |
https://doi.org/10.1007/s11063-019-10041-9 |
| remote_bool |
false |
| author2 |
Han, T. T. Gao, Z. |
| author2Str |
Han, T. T. Gao, Z. |
| ppnlink |
198692617 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11063-019-10041-9 |
| up_date |
2024-07-04T02:04:19.770Z |
| _version_ |
1803612229226987520 |
| 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">OLC2119715149</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230504171722.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230504s2019 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11063-019-10041-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2119715149</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11063-019-10041-9-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">000</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Liu, Y. B.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Pairwise Generalization Network for Cross-Domain Image Recognition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</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 2019</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In recent years, convolutional neural networks have received increasing attention from the computer vision and machine learning communities. Due to the differences in the distribution, tone and brightness of the training domain and test domain, researchers begin to focus on cross-domain image recognition. In this paper, we propose a Pairwise Generalization Network (PGN) for addressing the problem of cross-domain image recognition where Instance Normalization and Batch Normalization are added to enhance their abilities in the original domain and to expand to the new domain. Meanwhile, the Siamese architecture is utilized in the PGN to learn an embedding subspace that is discriminative, and map positive sample pairs aligned and negative sample pairs separated, which can work well even with only few labeled target data samples. We also add residual architecture and MMD loss for the PGN model to further improve its performance. Extensive experiments on two different public benchmarks show that our PGN solution significantly outperforms the state-of-the-art methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-domain</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pairwise</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, T. T.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gao, Z.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural processing letters</subfield><subfield code="d">Springer US, 1994</subfield><subfield code="g">52(2019), 2 vom: 16. Apr., Seite 1023-1041</subfield><subfield code="w">(DE-627)198692617</subfield><subfield code="w">(DE-600)1316823-X</subfield><subfield code="w">(DE-576)052842762</subfield><subfield code="x">1370-4621</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:52</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:2</subfield><subfield code="g">day:16</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:1023-1041</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11063-019-10041-9</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-PSY</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</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">52</subfield><subfield code="j">2019</subfield><subfield code="e">2</subfield><subfield code="b">16</subfield><subfield code="c">04</subfield><subfield code="h">1023-1041</subfield></datafield></record></collection>
|
| score |
7.3992653 |