Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/43AH7MS
Repositorysid.inpe.br/sibgrapi/2020/09.24.19.34
Last Update2020:10.01.16.55.58 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2020/09.24.19.34.16
Metadata Last Update2022:06.14.00.00.06 (UTC) administrator
DOI10.1109/SIBGRAPI51738.2020.00043
Citation KeyOliveiraPenaBert:2020:CoGrSe
TitleA comparison of graph-based semi-supervised learning for data augmentation
FormatOn-line
Year2020
Access Date2024, Sep. 16
Number of Files1
Size333 KiB
2. Context
Author1 Oliveira, Willian Dihanster G. de
2 Penatti, Otávio A. B.
3 Berton, Lilian
Affiliation1 Federal University of Sao Paulo
2 Samsung R&D Institute
3 Federal University of Sao Paulo
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
e-Mail Addresslberton@unifesp.br
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationPorto de Galinhas (virtual)
Date7-10 Nov. 2020
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2020-10-01 16:55:58 :: lberton@unifesp.br -> administrator :: 2020
2022-06-14 00:00:06 :: administrator -> lberton@unifesp.br :: 2020
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
KeywordsImage classification
data augmentation
image transformation
GANs
semi-supervised learning
machine learning
AbstractIn supervised learning, the algorithm accuracy usually improves with the size of the labeled dataset used for training the classifier. However, in many real-life scenarios, obtaining enough labeled data is costly or even not possible. In many circumstances, Data Augmentation (DA) techniques are usually employed, generating more labeled data for training machine learning algorithms. The common DA techniques are applied to already labeled data, generating simple variations of this data. For example, for image classification, image samples are rotated, cropped, flipped or other operators to generate variations of input image samples, and keeping their original labels. Other options are using Neural Networks algorithms that create new synthetic data or to employ Semi-supervised Learning (SSL) that label existing unlabeled data. In this paper, we perform a comparison among graph-based semi-supervised learning (GSSL) algorithms to augment the labeled dataset. The main advantage of using GSSL is that we can increase the training set by adding non-annotated images to the training set, therefore, we can benefit from the huge amount of unlabeled data available. Experiments are performed on five datasets for recognition of handwritten digits and letters (MNIST and EMINIST), animals (Dogs vs Cats), clothes (MNIST-Fashion) and remote sensing images (Brazilian Coffee Scenes), in which we compare different possibilities for DA, including the GSSL, Generative Adversarial Networks (GANs) and traditional Image Transformations (IT) applied on input labeled data. We also evaluated the impact of such techniques on different convolutional neural networks (CNN). Results indicate that, although all DA techniques performed well, GSSL was more robust to different image properties, presenting less accuracy variation across datasets.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2020 > A comparison of...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > A comparison of...
doc Directory Contentaccess
source Directory Content
Sibgrapi2020_ID30.pdf 24/09/2020 16:34 561.9 KiB 
agreement Directory Content
agreement.html 24/09/2020 16:34 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/43AH7MS
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/43AH7MS
Languageen
Target Filesibgrapi2020_ID30.pdf
User Grouplberton@unifesp.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/43G4L9S
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2020/10.28.20.46 24
sid.inpe.br/sibgrapi/2022/06.10.21.49 5
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
7. Description control
e-Mail (login)lberton@unifesp.br
update 


Close