Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/45CTEAE
Repositorysid.inpe.br/sibgrapi/2021/09.06.14.26
Last Update2021:09.06.14.26.37 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.06.14.26.37
Metadata Last Update2022:09.10.00.16.17 (UTC) administrator
Citation KeyJordãoSchw:2021:DeSpOd
TitlePartial Least Squares: A Deep Space Odyssey
FormatOn-line
Year2021
Access Date2024, Apr. 26
Number of Files1
Size473 KiB
2. Context
Author1 Jordão, Artur
2 Schwartz, William Robson
Affiliation1 Federal University of Minas Gerais
2 Federal University of Minas Gerais
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 Addressarturjordao@dcc.ufmg.br
Conference NameConference on Graphics, Patterns and Images, 34 (SIBGRAPI)
Conference LocationGramado, RS, Brazil (virtual)
Date18-22 Oct. 2021
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
Book TitleProceedings
Tertiary TypeMaster's or Doctoral Work
History (UTC)2021-09-06 14:26:37 :: arturjordao@dcc.ufmg.br -> administrator ::
2022-09-10 00:16:17 :: administrator -> :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
KeywordsComputing
computer vision
estimation theory
pattern recognition
AbstractModern visual pattern recognition models are based on deep convolutional networks. Such models are computationally expensive, hindering applicability on resource-constrained devices. To handle this problem, we propose three strategies. The first removes unimportant structures (neurons or layers) of convolutional networks, reducing their computational cost. The second inserts structures to design architectures automatically, enabling us to build high-performance networks. The third combines multiple layers of convolutional networks, enhancing data representation at negligible additional cost. These strategies are based on Partial Least Squares (PLS) which, despite promising results, is infeasible on large datasets due to memory constraints. To address this issue, we also propose a discriminative and low-complexity incremental PLS that learns a compact representation of the data using a single sample at a time, thus enabling applicability on large datasets. We assess the effectiveness of our approaches on several convolutional architectures and computer vision tasks, which include image classification, face verification and activity recognition. Our approaches reduce the resource overhead of both convolutional networks and Partial Least Squares, promoting energy- and hardware-friendly models for the academy and industry scenarios. Compared to state-of-the-art methods for the same purpose, we obtain one of the best trade-offs between predictive ability and computational cost.
Arrangementurlib.net > SDLA > Fonds > SIBGRAPI 2021 > Partial Least Squares:...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 06/09/2021 11:26 1.3 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45CTEAE
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45CTEAE
Languageen
Target FileArticle.pdf
User Grouparturjordao@dcc.ufmg.br
Visibilityshown
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/45PQ3RS
Citing Item Listsid.inpe.br/sibgrapi/2021/11.12.11.46 2
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi 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 versiontype volume


Close