Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/45CFHKL
Repositorysid.inpe.br/sibgrapi/2021/09.03.21.30
Last Update2021:09.03.21.30.51 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.03.21.30.51
Metadata Last Update2022:06.14.00.00.23 (UTC) administrator
DOI10.1109/SIBGRAPI54419.2021.00036
Citation KeySantosThumPont:2021:DaAuGu
TitleData Augmentation Guidelines for Cross-Dataset Transfer Learning and Pseudo Labeling
FormatOn-line
Year2021
Access Date2024, Apr. 26
Number of Files1
Size2915 KiB
2. Context
Author1 Santos, Fernando Pereira dos
2 Thumé, Gabriela Salvador
3 Ponti, Moacir Antonelli
Affiliation1 Universidade de São Paulo 
2 Universidade de São Paulo 
3 Universidade de São Paulo
EditorPaiva, Afonso
Menotti, David
Baranoski, Gladimir V. G.
Proença, Hugo Pedro
Junior, Antonio Lopes Apolinario
Papa, João Paulo
Pagliosa, Paulo
dos Santos, Thiago Oliveira
e Sá, Asla Medeiros
da Silveira, Thiago Lopes Trugillo
Brazil, Emilio Vital
Ponti, Moacir A.
Fernandes, Leandro A. F.
Avila, Sandra
e-Mail Addressfernando_persan@alumni.usp.br
Conference NameConference on Graphics, Patterns and Images, 34 (SIBGRAPI)
Conference LocationGramado, RS, Brazil (virtual)
Date18-22 Oct. 2021
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2021-09-03 21:30:51 :: fernando_persan@alumni.usp.br -> administrator ::
2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021
2022-03-02 13:36:07 :: menottid@gmail.com -> administrator :: 2021
2022-06-14 00:00:23 :: administrator -> :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordstransfer learning
deep learning
data augmentation
AbstractConvolutional Neural Networks require large amounts of labeled data in order to be trained. To improve such performances, a practical approach widely used is to augment the training set data, generating compatible data. Standard data augmentation for images includes conventional techniques, such as rotation, shift, and flip. In this paper, we go beyond such methods by studying alternative augmentation procedures for cross-dataset scenarios, in which a source dataset is used for training and a target dataset is used for testing. Through an extensive analysis considering different paradigms, saturation, and combination procedures, we provide guidelines for using augmentation methods in favor of transfer learning scenarios. As a novel approach for self-supervised learning, we also propose data augmentation techniques as pseudo labels during training. Our techniques demonstrate themselves as robust alternatives for different domains of transfer learning, including benefiting scenarios for self-supervised learning.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Data Augmentation Guidelines...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Data Augmentation Guidelines...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 03/09/2021 18:30 1.3 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45CFHKL
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45CFHKL
Languageen
Target Filepaper112.pdf
User Groupfernando_persan@alumni.usp.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/45PQ3RS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2021/11.12.11.46 4
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume


Close