Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Last Update2017: administrator
Metadata Last Update2020: administrator
Citation KeyAriasRamí:2017:SeAp
TitleLearning to Cluster with Auxiliary Tasks: A Semi-Supervised Approach
DateOct. 17-20, 2017
Access Date2021, Jan. 21
Number of Files1
Size657 KiB
Context area
Author1 Arias, Jhosimar George
2 Ramírez, Gerberth Adín
EditorTorchelsen, Rafael Piccin
Nascimento, Erickson Rangel do
Panozzo, Daniele
Liu, Zicheng
Farias, Mylène
Viera, Thales
Sacht, Leonardo
Ferreira, Nivan
Comba, João Luiz Dihl
Hirata, Nina
Schiavon Porto, Marcelo
Vital, Creto
Pagot, Christian Azambuja
Petronetto, Fabiano
Clua, Esteban
Cardeal, Flávio
Conference NameConference on Graphics, Patterns and Images, 30 (SIBGRAPI)
Conference LocationNiterói, RJ
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
History2017-08-21 21:30:41 :: -> administrator ::
2020-02-19 02:01:34 :: administrator -> :: 2017
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Content TypeExternal Contribution
Keywordsdeep learning, generative models, clustering, semi-supervised learning, probabilistic models.
AbstractIn this paper, we propose a model to learn a feature-category latent representation of the data, that is guided by a semi-supervised auxiliary task. The goal of this auxiliary task is to assign labels to unlabeled data and regularize the feature space. Our model is represented by a modified version of a Categorical Variational Autoencoder, i.e., a probabilistic generative model that approximates a categorical distribution with variational inference. We benefit from the autoencoders architecture to learn powerful representations with Deep Neural Networks in an unsupervised way, and to optimize the model with semi-supervised tasks. We derived a loss function that integrates the probabilistic model with our auxiliary task to guide the learning process. Experimental results show the effectiveness of our method achieving more than 90% of clustering accuracy by using only 100 labeled examples. Moreover we show that the learned features have discriminative properties that can be used for classification.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 21/08/2017 18:30 1.2 KiB 
Conditions of access and use area
data URL
zipped data URL
Target File138.pdf
Update Permissionnot transferred
Allied materials area
Next Higher Units8JMKD3MGPAW/3PJT9LS
Notes area
Empty Fieldsaccessionnumber affiliation archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume