Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition
Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Li, Minghui [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2023 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| Übergeordnetes Werk: |
Enthalten in: Neural computing & applications - Springer London, 1993, 35(2023), 28 vom: 05. Aug., Seite 21275-21290 |
|---|---|
| Übergeordnetes Werk: |
volume:35 ; year:2023 ; number:28 ; day:05 ; month:08 ; pages:21275-21290 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00521-023-08787-4 |
|---|
| Katalog-ID: |
OLC2145281797 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2145281797 | ||
| 003 | DE-627 | ||
| 005 | 20240118103716.0 | ||
| 007 | tu | ||
| 008 | 240118s2023 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00521-023-08787-4 |2 doi | |
| 035 | |a (DE-627)OLC2145281797 | ||
| 035 | |a (DE-He213)s00521-023-08787-4-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q VZ |
| 100 | 1 | |a Li, Minghui |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| 264 | 1 | |c 2023 | |
| 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 © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. | ||
| 650 | 4 | |a Fine-grained classification | |
| 650 | 4 | |a Few-shot learning | |
| 650 | 4 | |a Visual attention | |
| 650 | 4 | |a Batch Nuclear-norm maximization | |
| 700 | 1 | |a Yao, Hongxun |4 aut | |
| 700 | 1 | |a Wang, Yong |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Neural computing & applications |d Springer London, 1993 |g 35(2023), 28 vom: 05. Aug., Seite 21275-21290 |w (DE-627)165669608 |w (DE-600)1136944-9 |w (DE-576)032873050 |x 0941-0643 |7 nnns |
| 773 | 1 | 8 | |g volume:35 |g year:2023 |g number:28 |g day:05 |g month:08 |g pages:21275-21290 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00521-023-08787-4 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4277 | ||
| 951 | |a AR | ||
| 952 | |d 35 |j 2023 |e 28 |b 05 |c 08 |h 21275-21290 | ||
| author_variant |
m l ml h y hy y w yw |
|---|---|
| matchkey_str |
article:09410643:2023----::ounacadoadiestepoigoanpcfcieri |
| hierarchy_sort_str |
2023 |
| publishDate |
2023 |
| allfields |
10.1007/s00521-023-08787-4 doi (DE-627)OLC2145281797 (DE-He213)s00521-023-08787-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Minghui verfasserin aut Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization Yao, Hongxun aut Wang, Yong aut Enthalten in Neural computing & applications Springer London, 1993 35(2023), 28 vom: 05. Aug., Seite 21275-21290 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 https://doi.org/10.1007/s00521-023-08787-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 35 2023 28 05 08 21275-21290 |
| spelling |
10.1007/s00521-023-08787-4 doi (DE-627)OLC2145281797 (DE-He213)s00521-023-08787-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Minghui verfasserin aut Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization Yao, Hongxun aut Wang, Yong aut Enthalten in Neural computing & applications Springer London, 1993 35(2023), 28 vom: 05. Aug., Seite 21275-21290 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 https://doi.org/10.1007/s00521-023-08787-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 35 2023 28 05 08 21275-21290 |
| allfields_unstemmed |
10.1007/s00521-023-08787-4 doi (DE-627)OLC2145281797 (DE-He213)s00521-023-08787-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Minghui verfasserin aut Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization Yao, Hongxun aut Wang, Yong aut Enthalten in Neural computing & applications Springer London, 1993 35(2023), 28 vom: 05. Aug., Seite 21275-21290 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 https://doi.org/10.1007/s00521-023-08787-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 35 2023 28 05 08 21275-21290 |
| allfieldsGer |
10.1007/s00521-023-08787-4 doi (DE-627)OLC2145281797 (DE-He213)s00521-023-08787-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Minghui verfasserin aut Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization Yao, Hongxun aut Wang, Yong aut Enthalten in Neural computing & applications Springer London, 1993 35(2023), 28 vom: 05. Aug., Seite 21275-21290 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 https://doi.org/10.1007/s00521-023-08787-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 35 2023 28 05 08 21275-21290 |
| allfieldsSound |
10.1007/s00521-023-08787-4 doi (DE-627)OLC2145281797 (DE-He213)s00521-023-08787-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Minghui verfasserin aut Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization Yao, Hongxun aut Wang, Yong aut Enthalten in Neural computing & applications Springer London, 1993 35(2023), 28 vom: 05. Aug., Seite 21275-21290 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 https://doi.org/10.1007/s00521-023-08787-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 35 2023 28 05 08 21275-21290 |
| language |
English |
| source |
Enthalten in Neural computing & applications 35(2023), 28 vom: 05. Aug., Seite 21275-21290 volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 |
| sourceStr |
Enthalten in Neural computing & applications 35(2023), 28 vom: 05. Aug., Seite 21275-21290 volume:35 year:2023 number:28 day:05 month:08 pages:21275-21290 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Neural computing & applications |
| authorswithroles_txt_mv |
Li, Minghui @@aut@@ Yao, Hongxun @@aut@@ Wang, Yong @@aut@@ |
| publishDateDaySort_date |
2023-08-05T00:00:00Z |
| hierarchy_top_id |
165669608 |
| dewey-sort |
14 |
| id |
OLC2145281797 |
| 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">OLC2145281797</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118103716.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2023 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-023-08787-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2145281797</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-023-08787-4-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">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Li, Minghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</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">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fine-grained classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Few-shot learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual attention</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Batch Nuclear-norm maximization</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yao, Hongxun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Yong</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">35(2023), 28 vom: 05. Aug., Seite 21275-21290</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:35</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:28</subfield><subfield code="g">day:05</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:21275-21290</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-023-08787-4</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">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">35</subfield><subfield code="j">2023</subfield><subfield code="e">28</subfield><subfield code="b">05</subfield><subfield code="c">08</subfield><subfield code="h">21275-21290</subfield></datafield></record></collection>
|
| author |
Li, Minghui |
| spellingShingle |
Li, Minghui ddc 004 misc Fine-grained classification misc Few-shot learning misc Visual attention misc Batch Nuclear-norm maximization Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| authorStr |
Li, Minghui |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)165669608 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0941-0643 |
| topic_title |
004 VZ Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition Fine-grained classification Few-shot learning Visual attention Batch Nuclear-norm maximization |
| topic |
ddc 004 misc Fine-grained classification misc Few-shot learning misc Visual attention misc Batch Nuclear-norm maximization |
| topic_unstemmed |
ddc 004 misc Fine-grained classification misc Few-shot learning misc Visual attention misc Batch Nuclear-norm maximization |
| topic_browse |
ddc 004 misc Fine-grained classification misc Few-shot learning misc Visual attention misc Batch Nuclear-norm maximization |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Neural computing & applications |
| hierarchy_parent_id |
165669608 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Neural computing & applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 |
| title |
Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| ctrlnum |
(DE-627)OLC2145281797 (DE-He213)s00521-023-08787-4-p |
| title_full |
Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| author_sort |
Li, Minghui |
| journal |
Neural computing & applications |
| journalStr |
Neural computing & applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2023 |
| contenttype_str_mv |
txt |
| container_start_page |
21275 |
| author_browse |
Li, Minghui Yao, Hongxun Wang, Yong |
| container_volume |
35 |
| class |
004 VZ |
| format_se |
Aufsätze |
| author-letter |
Li, Minghui |
| doi_str_mv |
10.1007/s00521-023-08787-4 |
| dewey-full |
004 |
| title_sort |
focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| title_auth |
Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| abstract |
Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstractGer |
Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstract_unstemmed |
Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 |
| container_issue |
28 |
| title_short |
Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition |
| url |
https://doi.org/10.1007/s00521-023-08787-4 |
| remote_bool |
false |
| author2 |
Yao, Hongxun Wang, Yong |
| author2Str |
Yao, Hongxun Wang, Yong |
| ppnlink |
165669608 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00521-023-08787-4 |
| up_date |
2024-07-04T02:36:17.588Z |
| _version_ |
1803614240209108992 |
| 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">OLC2145281797</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118103716.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2023 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-023-08787-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2145281797</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-023-08787-4-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">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Li, Minghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</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">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In real-world industrial applications, learning to recognize novel visual categories from a few samples is challenging and promising. Although some efforts have been made in the academic field for few-shot classification studies, there is still a lack of high-precision fine-grained few-shot classification models in some specific fields, especially in the fine-grained agricultural field. As far as we know, this study is the first work on meta-learning few-shot classification for fine-grained plant disease classification (specific to disease severity). We propose a multi-perspective hybrid attention meta-learning model based on a Batch Nuclear-norm constraint. The model explores discriminative features by focusing on key regions, and the hybrid attention module is divided into two sub-modules, soft attention model and patch-hard attention model. The discriminability and diversity constraint module is introduced in the loss function to constrain the Batch Nuclear-norm of the classification matrix, which improves the discriminative properties of the classification model and increases its diversity at the same time. In this paper, a large number of experiments have been carried out on multiple datasets. The experimental results demonstrate that our work has better performance than state-of-the-art models. It can be said that our work is a valuable supplement to the domain-specific industrial application models.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fine-grained classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Few-shot learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual attention</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Batch Nuclear-norm maximization</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yao, Hongxun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Yong</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">35(2023), 28 vom: 05. Aug., Seite 21275-21290</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:35</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:28</subfield><subfield code="g">day:05</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:21275-21290</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-023-08787-4</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">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">35</subfield><subfield code="j">2023</subfield><subfield code="e">28</subfield><subfield code="b">05</subfield><subfield code="c">08</subfield><subfield code="h">21275-21290</subfield></datafield></record></collection>
|
| score |
7.3977823 |