Fechar
Metadados

1. Identificação
Tipo de ReferênciaArtigo em Evento (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Código do Detentoribi 8JMKD3MGPEW34M/46T9EHH
Identificador8JMKD3MGPEW34M/43AH7MS
Repositóriosid.inpe.br/sibgrapi/2020/09.24.19.34
Última Atualização2020:10.01.16.55.58 (UTC) administrator
Repositório de Metadadossid.inpe.br/sibgrapi/2020/09.24.19.34.16
Última Atualização dos Metadados2022:06.14.00.00.06 (UTC) administrator
DOI10.1109/SIBGRAPI51738.2020.00043
Chave de CitaçãoOliveiraPenaBert:2020:CoGrSe
TítuloA comparison of graph-based semi-supervised learning for data augmentation
FormatoOn-line
Ano2020
Data de Acesso17 maio 2024
Número de Arquivos1
Tamanho333 KiB
2. Contextualização
Autor1 Oliveira, Willian Dihanster G. de
2 Penatti, Otávio A. B.
3 Berton, Lilian
Afiliação1 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)
Endereço de e-Maillberton@unifesp.br
Nome do EventoConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Localização do EventoPorto de Galinhas (virtual)
Data7-10 Nov. 2020
Editora (Publisher)IEEE Computer Society
Cidade da EditoraLos Alamitos
Título do LivroProceedings
Tipo TerciárioFull Paper
Histórico (UTC)2020-10-01 16:55:58 :: lberton@unifesp.br -> administrator :: 2020
2022-06-14 00:00:06 :: administrator -> lberton@unifesp.br :: 2020
3. Conteúdo e estrutura
É a matriz ou uma cópia?é a matriz
Estágio do Conteúdoconcluido
Transferível1
Tipo de Versãofinaldraft
Palavras-ChaveImage classification
data augmentation
image transformation
GANs
semi-supervised learning
machine learning
ResumoIn 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.
Arranjo 1urlib.net > SDLA > Fonds > SIBGRAPI 2020 > A comparison of...
Arranjo 2urlib.net > SDLA > Fonds > Full Index > A comparison of...
Conteúdo da Pasta docacessar
Conteúdo da Pasta source
Sibgrapi2020_ID30.pdf 24/09/2020 16:34 561.9 KiB 
Conteúdo da Pasta agreement
agreement.html 24/09/2020 16:34 1.2 KiB 
4. Condições de acesso e uso
URL dos dadoshttp://urlib.net/ibi/8JMKD3MGPEW34M/43AH7MS
URL dos dados zipadoshttp://urlib.net/zip/8JMKD3MGPEW34M/43AH7MS
Idiomaen
Arquivo Alvosibgrapi2020_ID30.pdf
Grupo de Usuárioslberton@unifesp.br
Visibilidadeshown
Permissão de Atualizaçãonão transferida
5. Fontes relacionadas
Repositório Espelhosid.inpe.br/banon/2001/03.30.15.38.24
Unidades Imediatamente Superiores8JMKD3MGPEW34M/43G4L9S
8JMKD3MGPEW34M/4742MCS
Lista de Itens Citandosid.inpe.br/sibgrapi/2020/10.28.20.46 6
sid.inpe.br/sibgrapi/2022/06.10.21.49 1
Acervo Hospedeirosid.inpe.br/banon/2001/03.30.15.38
6. Notas
Campos Vaziosarchivingpolicy 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. Controle da descrição
e-Mail (login)lberton@unifesp.br
atualizar 


Fechar