Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/45EACT2
Repositorysid.inpe.br/sibgrapi/2021/09.15.00.27
Last Update2021:09.15.00.27.19 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.15.00.27.20
Metadata Last Update2022:06.14.00.00.34 (UTC) administrator
DOI10.1109/SIBGRAPI54419.2021.00062
Citation KeyMoraesEvanFernMart:2021:GeCoOu
TitleGCOOD: A Generic Coupled Out-of-Distribution Detector for Robust Classification
FormatOn-line
Year2021
Access Date2024, Apr. 25
Number of Files1
Size843 KiB
2. Context
Author1 Moraes, Rogério Ferreira de
2 Evangelista, Raphael dos S.
3 Fernandes, Leandro A. F.
4 Martí, Luis
Affiliation1 Universidade Federal Fluminense (UFF), Niterói, Brazil 
2 Universidade Federal Fluminense (UFF), Niterói, Brazil 
3 Universidade Federal Fluminense (UFF), Niterói, Brazil 
4 Inria Chile Research Center, Las Condes, Chile
EditorPaiva, Afonso
Menotti, David
Baranoski, Gladimir V. G.
Proença, Hugo Pedro
Junior, Antonio Lopes Apolinario
Papa, Joăo 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 Addressrogeriofm@id.uff.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)2021-09-15 00:28:46 :: rogeriofm@id.uff.br -> administrator :: 2021
2022-03-02 00:54:16 :: administrator -> menottid@gmail.com :: 2021
2022-03-02 13:31:58 :: menottid@gmail.com -> administrator :: 2021
2022-06-14 00:00:34 :: administrator -> :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
KeywordsOOD
Voronoi diagrams
AbstractNeural networks have achieved high degrees of accuracy in classification tasks. However, when an out-of-distribution (OOD) sample (\emph{i.e.,}~entries from unknown classes) is submitted to the classification process, the result is the association of the sample to one or more of the trained classes with different degrees of confidence. If any of these confidence values are more significant than the user-defined threshold, the network will mislabel the sample, affecting the model credibility. The definition of the acceptance threshold itself is a sensitive issue in the face of the classifier's overconfidence. This paper presents the Generic Coupled OOD Detector (GCOOD), a novel Convolutional Neural Network (CNN) tailored to detect whether an entry submitted to a trained classification model is an OOD sample for that model. From the analysis of the Softmax output of any classifier, our approach can indicate whether the resulting classification should be considered or not as a sample of some of the trained classes. To train our CNN, we had to develop a novel training strategy based on Voronoi diagrams of the location of representative entries in the latent space of the classification model and graph coloring. We evaluated our approach using ResNet, VGG, DenseNet, and SqueezeNet classifiers with images from the CIFAR-10 dataset.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2021 > GCOOD: A Generic...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > GCOOD: A Generic...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 14/09/2021 21:27 1.3 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45EACT2
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45EACT2
Languageen
Target File2021___Moraes_et_al____SIBGRAPI.pdf
User Grouprogeriofm@id.uff.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 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