An overview of mixing augmentation methods and augmentation strategies
Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Lewy, Dominik [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s) 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Artificial intelligence review - Springer Netherlands, 1987, 56(2022), 3 vom: 30. Juni, Seite 2111-2169 |
|---|---|
| Übergeordnetes Werk: |
volume:56 ; year:2022 ; number:3 ; day:30 ; month:06 ; pages:2111-2169 |
| Links: |
|---|
| DOI / URN: |
10.1007/s10462-022-10227-z |
|---|
| Katalog-ID: |
OLC2134002891 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2134002891 | ||
| 003 | DE-627 | ||
| 005 | 20230506160114.0 | ||
| 007 | tu | ||
| 008 | 230506s2022 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10462-022-10227-z |2 doi | |
| 035 | |a (DE-627)OLC2134002891 | ||
| 035 | |a (DE-He213)s10462-022-10227-z-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q VZ |
| 084 | |a 54.00 |2 bkl | ||
| 100 | 1 | |a Lewy, Dominik |e verfasserin |0 (orcid)0000-0003-2107-4909 |4 aut | |
| 245 | 1 | 0 | |a An overview of mixing augmentation methods and augmentation strategies |
| 264 | 1 | |c 2022 | |
| 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) 2022 | ||
| 520 | |a Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. | ||
| 650 | 4 | |a Data augmentation | |
| 650 | 4 | |a Image data | |
| 650 | 4 | |a Regularization | |
| 650 | 4 | |a Mixing images | |
| 650 | 4 | |a Augmentation strategies | |
| 700 | 1 | |a Mańdziuk, Jacek |0 (orcid)0000-0003-0947-028X |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Artificial intelligence review |d Springer Netherlands, 1987 |g 56(2022), 3 vom: 30. Juni, Seite 2111-2169 |w (DE-627)129223018 |w (DE-600)56633-0 |w (DE-576)014458209 |x 0269-2821 |7 nnns |
| 773 | 1 | 8 | |g volume:56 |g year:2022 |g number:3 |g day:30 |g month:06 |g pages:2111-2169 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s10462-022-10227-z |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 936 | b | k | |a 54.00 |q VZ |
| 951 | |a AR | ||
| 952 | |d 56 |j 2022 |e 3 |b 30 |c 06 |h 2111-2169 | ||
| author_variant |
d l dl j m jm |
|---|---|
| matchkey_str |
article:02692821:2022----::nvriwfiigumnainehdadum |
| hierarchy_sort_str |
2022 |
| bklnumber |
54.00 |
| publishDate |
2022 |
| allfields |
10.1007/s10462-022-10227-z doi (DE-627)OLC2134002891 (DE-He213)s10462-022-10227-z-p DE-627 ger DE-627 rakwb eng 004 VZ 54.00 bkl Lewy, Dominik verfasserin (orcid)0000-0003-2107-4909 aut An overview of mixing augmentation methods and augmentation strategies 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. Data augmentation Image data Regularization Mixing images Augmentation strategies Mańdziuk, Jacek (orcid)0000-0003-0947-028X aut Enthalten in Artificial intelligence review Springer Netherlands, 1987 56(2022), 3 vom: 30. Juni, Seite 2111-2169 (DE-627)129223018 (DE-600)56633-0 (DE-576)014458209 0269-2821 nnns volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 https://doi.org/10.1007/s10462-022-10227-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.00 VZ AR 56 2022 3 30 06 2111-2169 |
| spelling |
10.1007/s10462-022-10227-z doi (DE-627)OLC2134002891 (DE-He213)s10462-022-10227-z-p DE-627 ger DE-627 rakwb eng 004 VZ 54.00 bkl Lewy, Dominik verfasserin (orcid)0000-0003-2107-4909 aut An overview of mixing augmentation methods and augmentation strategies 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. Data augmentation Image data Regularization Mixing images Augmentation strategies Mańdziuk, Jacek (orcid)0000-0003-0947-028X aut Enthalten in Artificial intelligence review Springer Netherlands, 1987 56(2022), 3 vom: 30. Juni, Seite 2111-2169 (DE-627)129223018 (DE-600)56633-0 (DE-576)014458209 0269-2821 nnns volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 https://doi.org/10.1007/s10462-022-10227-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.00 VZ AR 56 2022 3 30 06 2111-2169 |
| allfields_unstemmed |
10.1007/s10462-022-10227-z doi (DE-627)OLC2134002891 (DE-He213)s10462-022-10227-z-p DE-627 ger DE-627 rakwb eng 004 VZ 54.00 bkl Lewy, Dominik verfasserin (orcid)0000-0003-2107-4909 aut An overview of mixing augmentation methods and augmentation strategies 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. Data augmentation Image data Regularization Mixing images Augmentation strategies Mańdziuk, Jacek (orcid)0000-0003-0947-028X aut Enthalten in Artificial intelligence review Springer Netherlands, 1987 56(2022), 3 vom: 30. Juni, Seite 2111-2169 (DE-627)129223018 (DE-600)56633-0 (DE-576)014458209 0269-2821 nnns volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 https://doi.org/10.1007/s10462-022-10227-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.00 VZ AR 56 2022 3 30 06 2111-2169 |
| allfieldsGer |
10.1007/s10462-022-10227-z doi (DE-627)OLC2134002891 (DE-He213)s10462-022-10227-z-p DE-627 ger DE-627 rakwb eng 004 VZ 54.00 bkl Lewy, Dominik verfasserin (orcid)0000-0003-2107-4909 aut An overview of mixing augmentation methods and augmentation strategies 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. Data augmentation Image data Regularization Mixing images Augmentation strategies Mańdziuk, Jacek (orcid)0000-0003-0947-028X aut Enthalten in Artificial intelligence review Springer Netherlands, 1987 56(2022), 3 vom: 30. Juni, Seite 2111-2169 (DE-627)129223018 (DE-600)56633-0 (DE-576)014458209 0269-2821 nnns volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 https://doi.org/10.1007/s10462-022-10227-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.00 VZ AR 56 2022 3 30 06 2111-2169 |
| allfieldsSound |
10.1007/s10462-022-10227-z doi (DE-627)OLC2134002891 (DE-He213)s10462-022-10227-z-p DE-627 ger DE-627 rakwb eng 004 VZ 54.00 bkl Lewy, Dominik verfasserin (orcid)0000-0003-2107-4909 aut An overview of mixing augmentation methods and augmentation strategies 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. Data augmentation Image data Regularization Mixing images Augmentation strategies Mańdziuk, Jacek (orcid)0000-0003-0947-028X aut Enthalten in Artificial intelligence review Springer Netherlands, 1987 56(2022), 3 vom: 30. Juni, Seite 2111-2169 (DE-627)129223018 (DE-600)56633-0 (DE-576)014458209 0269-2821 nnns volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 https://doi.org/10.1007/s10462-022-10227-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.00 VZ AR 56 2022 3 30 06 2111-2169 |
| language |
English |
| source |
Enthalten in Artificial intelligence review 56(2022), 3 vom: 30. Juni, Seite 2111-2169 volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 |
| sourceStr |
Enthalten in Artificial intelligence review 56(2022), 3 vom: 30. Juni, Seite 2111-2169 volume:56 year:2022 number:3 day:30 month:06 pages:2111-2169 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Data augmentation Image data Regularization Mixing images Augmentation strategies |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Artificial intelligence review |
| authorswithroles_txt_mv |
Lewy, Dominik @@aut@@ Mańdziuk, Jacek @@aut@@ |
| publishDateDaySort_date |
2022-06-30T00:00:00Z |
| hierarchy_top_id |
129223018 |
| dewey-sort |
14 |
| id |
OLC2134002891 |
| 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">OLC2134002891</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506160114.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230506s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10462-022-10227-z</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2134002891</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10462-022-10227-z-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="084" ind1=" " ind2=" "><subfield code="a">54.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lewy, Dominik</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-2107-4909</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An overview of mixing augmentation methods and augmentation strategies</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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) 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Data augmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image data</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Regularization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Mixing images</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Augmentation strategies</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mańdziuk, Jacek</subfield><subfield code="0">(orcid)0000-0003-0947-028X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Artificial intelligence review</subfield><subfield code="d">Springer Netherlands, 1987</subfield><subfield code="g">56(2022), 3 vom: 30. Juni, Seite 2111-2169</subfield><subfield code="w">(DE-627)129223018</subfield><subfield code="w">(DE-600)56633-0</subfield><subfield code="w">(DE-576)014458209</subfield><subfield code="x">0269-2821</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:56</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:3</subfield><subfield code="g">day:30</subfield><subfield code="g">month:06</subfield><subfield code="g">pages:2111-2169</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10462-022-10227-z</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="936" ind1="b" ind2="k"><subfield code="a">54.00</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">56</subfield><subfield code="j">2022</subfield><subfield code="e">3</subfield><subfield code="b">30</subfield><subfield code="c">06</subfield><subfield code="h">2111-2169</subfield></datafield></record></collection>
|
| author |
Lewy, Dominik |
| spellingShingle |
Lewy, Dominik ddc 004 bkl 54.00 misc Data augmentation misc Image data misc Regularization misc Mixing images misc Augmentation strategies An overview of mixing augmentation methods and augmentation strategies |
| authorStr |
Lewy, Dominik |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129223018 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0269-2821 |
| topic_title |
004 VZ 54.00 bkl An overview of mixing augmentation methods and augmentation strategies Data augmentation Image data Regularization Mixing images Augmentation strategies |
| topic |
ddc 004 bkl 54.00 misc Data augmentation misc Image data misc Regularization misc Mixing images misc Augmentation strategies |
| topic_unstemmed |
ddc 004 bkl 54.00 misc Data augmentation misc Image data misc Regularization misc Mixing images misc Augmentation strategies |
| topic_browse |
ddc 004 bkl 54.00 misc Data augmentation misc Image data misc Regularization misc Mixing images misc Augmentation strategies |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Artificial intelligence review |
| hierarchy_parent_id |
129223018 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Artificial intelligence review |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129223018 (DE-600)56633-0 (DE-576)014458209 |
| title |
An overview of mixing augmentation methods and augmentation strategies |
| ctrlnum |
(DE-627)OLC2134002891 (DE-He213)s10462-022-10227-z-p |
| title_full |
An overview of mixing augmentation methods and augmentation strategies |
| author_sort |
Lewy, Dominik |
| journal |
Artificial intelligence review |
| journalStr |
Artificial intelligence review |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
2111 |
| author_browse |
Lewy, Dominik Mańdziuk, Jacek |
| container_volume |
56 |
| class |
004 VZ 54.00 bkl |
| format_se |
Aufsätze |
| author-letter |
Lewy, Dominik |
| doi_str_mv |
10.1007/s10462-022-10227-z |
| normlink |
(ORCID)0000-0003-2107-4909 (ORCID)0000-0003-0947-028X |
| normlink_prefix_str_mv |
(orcid)0000-0003-2107-4909 (orcid)0000-0003-0947-028X |
| dewey-full |
004 |
| title_sort |
an overview of mixing augmentation methods and augmentation strategies |
| title_auth |
An overview of mixing augmentation methods and augmentation strategies |
| abstract |
Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. © The Author(s) 2022 |
| abstractGer |
Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. © The Author(s) 2022 |
| abstract_unstemmed |
Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021. © The Author(s) 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT |
| container_issue |
3 |
| title_short |
An overview of mixing augmentation methods and augmentation strategies |
| url |
https://doi.org/10.1007/s10462-022-10227-z |
| remote_bool |
false |
| author2 |
Mańdziuk, Jacek |
| author2Str |
Mańdziuk, Jacek |
| ppnlink |
129223018 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s10462-022-10227-z |
| up_date |
2024-07-03T22:52:28.684Z |
| _version_ |
1803600158979522560 |
| 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">OLC2134002891</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506160114.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230506s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10462-022-10227-z</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2134002891</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10462-022-10227-z-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="084" ind1=" " ind2=" "><subfield code="a">54.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lewy, Dominik</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-2107-4909</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An overview of mixing augmentation methods and augmentation strategies</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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) 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017–2021.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Data augmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image data</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Regularization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Mixing images</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Augmentation strategies</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mańdziuk, Jacek</subfield><subfield code="0">(orcid)0000-0003-0947-028X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Artificial intelligence review</subfield><subfield code="d">Springer Netherlands, 1987</subfield><subfield code="g">56(2022), 3 vom: 30. Juni, Seite 2111-2169</subfield><subfield code="w">(DE-627)129223018</subfield><subfield code="w">(DE-600)56633-0</subfield><subfield code="w">(DE-576)014458209</subfield><subfield code="x">0269-2821</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:56</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:3</subfield><subfield code="g">day:30</subfield><subfield code="g">month:06</subfield><subfield code="g">pages:2111-2169</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10462-022-10227-z</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="936" ind1="b" ind2="k"><subfield code="a">54.00</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">56</subfield><subfield code="j">2022</subfield><subfield code="e">3</subfield><subfield code="b">30</subfield><subfield code="c">06</subfield><subfield code="h">2111-2169</subfield></datafield></record></collection>
|
| score |
7.399453 |