<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<identifier>8JMKD3MGPAW/3PFRBBL</identifier>
		<repository>sid.inpe.br/sibgrapi/2017/08.21.21.30</repository>
		<lastupdate>2017:08.21.21.30.41 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2017/08.21.21.30.41</metadatarepository>
		<metadatalastupdate>2020:02.19.02.01.34 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2017}</metadatalastupdate>
		<citationkey>AriasRamí:2017:SeAp</citationkey>
		<title>Learning to Cluster with Auxiliary Tasks: A Semi-Supervised Approach</title>
		<format>On-line</format>
		<year>2017</year>
		<numberoffiles>1</numberoffiles>
		<size>657 KiB</size>
		<author>Arias, Jhosimar George,</author>
		<author>Ramírez, Gerberth Adín,</author>
		<editor>Torchelsen, Rafael Piccin,</editor>
		<editor>Nascimento, Erickson Rangel do,</editor>
		<editor>Panozzo, Daniele,</editor>
		<editor>Liu, Zicheng,</editor>
		<editor>Farias, Mylène,</editor>
		<editor>Viera, Thales,</editor>
		<editor>Sacht, Leonardo,</editor>
		<editor>Ferreira, Nivan,</editor>
		<editor>Comba, João Luiz Dihl,</editor>
		<editor>Hirata, Nina,</editor>
		<editor>Schiavon Porto, Marcelo,</editor>
		<editor>Vital, Creto,</editor>
		<editor>Pagot, Christian Azambuja,</editor>
		<editor>Petronetto, Fabiano,</editor>
		<editor>Clua, Esteban,</editor>
		<editor>Cardeal, Flávio,</editor>
		<e-mailaddress>jhosimar.figueroa@students.ic.unicamp.br</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)</conferencename>
		<conferencelocation>Niterói, RJ</conferencelocation>
		<date>Oct. 17-20, 2017</date>
		<booktitle>Proceedings</booktitle>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<tertiarytype>Full Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<contenttype>External Contribution</contenttype>
		<keywords>deep learning, generative models, clustering, semi-supervised learning, probabilistic models.</keywords>
		<abstract>In 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.</abstract>
		<language>en</language>
		<targetfile>138.pdf</targetfile>
		<usergroup>jhosimar.figueroa@students.ic.unicamp.br</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPAW/3PJT9LS</nexthigherunit>
		<nexthigherunit>8JMKD3MGPAW/3PKCC58</nexthigherunit>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2017/08.21.21.30</url>
	</metadata>
</metadatalist>