Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/43BDF3B
Repositorysid.inpe.br/sibgrapi/2020/09.30.02.48
Last Update2020:09.30.02.48.17 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2020/09.30.02.48.17
Metadata Last Update2022:06.14.00.00.14 (UTC) administrator
DOI10.1109/SIBGRAPI51738.2020.00035
Citation KeyAvelarTavSilJunLam:2020:SuImCl
TitleSuperpixel Image Classification with Graph Attention Networks
FormatOn-line
Year2020
Access Date2024, Dec. 21
Number of Files1
Size1548 KiB
2. Context
Author1 Avelar, Pedro Henrique da Costa
2 Tavares, Anderson Rocha
3 Silveira, Thiago Lopes Trugillo da
4 Jung, Cláudio Rosito
5 Lamb, Luís da Cunha
Affiliation1 Federal University of Rio Grande do Sul
2 Federal University of Rio Grande do Sul
3 University of Rio Grande
4 Federal University of Rio Grande do Sul
5 Federal University of Rio Grande do Sul
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
e-Mail Addressphcavelar@inf.ufrgs.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)2020-09-30 02:48:17 :: phcavelar@inf.ufrgs.br -> administrator ::
2022-06-14 00:00:14 :: administrator -> phcavelar@inf.ufrgs.br :: 2020
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordssuperpixel
graph attention networks
graph neural networks
AbstractThis paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-attention mechanisms, outperforms other GNN models. Although raw image classifiers perform better than GATs due to information loss during the RAG generation, our methodology opens an interesting avenue of research on deep learning beyond rectangular-gridded images, such as 360-degree field of view panoramas. Traditional convolutional kernels of current state-of-the-art methods cannot handle panoramas, whereas the adapted superpixel algorithms and the resulting region adjacency graphs can naturally feed a GNN, without topology issues.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2020 > Superpixel Image Classification...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Superpixel Image Classification...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 29/09/2020 23:48 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/43BDF3B
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/43BDF3B
Languageen
Target FilePID6630943.pdf
User Groupphcavelar@inf.ufrgs.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 48
sid.inpe.br/sibgrapi/2022/06.10.21.49 7
sid.inpe.br/banon/2001/03.30.15.38.24 1
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)phcavelar@inf.ufrgs.br
update 


Close