Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/45CUD68
Repositorysid.inpe.br/sibgrapi/2021/09.06.19.40
Last Update2021:09.06.19.40.09 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.06.19.40.09
Metadata Last Update2022:06.14.00.00.29 (UTC) administrator
DOI10.1109/SIBGRAPI54419.2021.00034
Citation KeyBenatoTeleFalc:2021:ItPsDe
TitleIterative Pseudo-Labeling with Deep Feature Annotation and Confidence-Based Sampling
FormatOn-line
Year2021
Access Date2024, May 07
Number of Files1
Size461 KiB
2. Context
Author1 Benato, Barbara Caroline
2 Telea, Alexandru Cristian
3 Falcão, Alexandre Xavier
Affiliation1 University of Campinas 
2 Utrecht University 
3 University of Campinas
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 Addressbarbarabenato@gmail.com
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 19:40:09 :: barbarabenato@gmail.com -> administrator ::
2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021
2022-03-02 13:21:11 :: 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
Keywordssemi-supervised learning
pseudolabels
optimum path forest
data annotation
AbstractTraining deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To address this issue, increased attention has been devoted to techniques that propagate uncertain labels (also called pseudo labels) to large amounts of unsupervised samples and use them for training the model. However, these techniques still need hundreds of supervised samples per class in the training set and a validation set with extra supervised samples to tune the model. We improve a recent iterative pseudo-labeling technique, Deep Feature Annotation (DeepFA), by selecting the most confident unsupervised samples to iteratively train a deep neural network. Our confidence-based sampling strategy relies on only dozens of annotated training samples per class with no validation set, considerably reducing user effort in data annotation. We first ascertain the best configuration for the baseline a self-trained deep neural network and then evaluate our confidence DeepFA for different confidence thresholds. Experiments on six datasets show that DeepFA already outperforms the self-trained baseline, but confidence DeepFA can considerably outperform the original DeepFA and the baseline.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Iterative Pseudo-Labeling with...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Iterative Pseudo-Labeling with...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 06/09/2021 16:40 1.3 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45CUD68
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45CUD68
Languageen
Target File2021_sibgrapi_Benato-2.pdf
User Groupbarbarabenato@gmail.com
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