Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/45CUEK8
Repositorysid.inpe.br/sibgrapi/2021/09.06.19.58
Last Update2021:09.06.19.58.55 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.06.19.58.55
Metadata Last Update2022:06.14.00.00.29 (UTC) administrator
DOI10.1109/SIBGRAPI54419.2021.00038
Citation KeyCavallariPont:2021:SeSiNe
TitleSemi-supervised siamese network using self-supervision under scarce annotation improves class separability and robustness to attack
FormatOn-line
Year2021
Access Date2024, May 06
Number of Files1
Size22476 KiB
2. Context
Author1 Cavallari, Gabriel
2 Ponti, Moacir
Affiliation1 Universidade de São Paulo 
2 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 Addressgabriel.cavallari@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)2021-09-06 19:58:55 :: gabriel.cavallari@usp.br -> administrator ::
2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021
2022-03-02 13:23:02 :: menottid@gmail.com -> administrator :: 2021
2022-06-14 00:00:29 :: administrator -> :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsdeep learning
attack
self-supervision
self-supervised learning
AbstractSelf-supervised learning approaches were shown to benefit feature learning by training models under a pretext task. In this context, learning from limited data can be tackled using a combination of semi-supervised learning and self-supervision. In this paper we combine the traditional supervised learning paradigm with the rotation prediction self-supervised task, that are used simultaneously to train a siamese model with a joint loss function and shared weights. In particular, we are interested in the case in which the proportion of labeled with respect to unlabeled data is small. We investigate the effectiveness of a compact feature space obtained after training under such limited annotation scenario, in terms of linear class separability and under attack. The study includes images from multiple domains, such as natural images (STL-10 dataset), products (Fashion-MNIST dataset) and biomedical images (Malaria dataset). We show that in scenarios where we have only a few labeled data the model augmented with a self-supervised task can take advantage of the unlabeled data to improve the learned representation in terms of the linear discrimination, as well as allowing learning even under attack. Also, we discuss the choices in terms of self-supervision and cases of failure considering the different datasets.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Semi-supervised siamese network...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Semi-supervised siamese network...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 06/09/2021 16:58 1.3 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45CUEK8
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45CUEK8
Languageen
Target File81.pdf
User Groupgabriel.cavallari@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 3
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