1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/45CTEAE |
Repository | sid.inpe.br/sibgrapi/2021/09.06.14.26 |
Last Update | 2021:09.06.14.26.37 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2021/09.06.14.26.37 |
Metadata Last Update | 2022:09.10.00.16.17 (UTC) administrator |
Citation Key | JordãoSchw:2021:DeSpOd |
Title | Partial Least Squares: A Deep Space Odyssey |
Format | On-line |
Year | 2021 |
Access Date | 2024, Apr. 26 |
Number of Files | 1 |
Size | 473 KiB |
|
2. Context | |
Author | 1 Jordão, Artur 2 Schwartz, William Robson |
Affiliation | 1 Federal University of Minas Gerais 2 Federal University of Minas Gerais |
Editor | Paiva, 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 Address | arturjordao@dcc.ufmg.br |
Conference Name | Conference on Graphics, Patterns and Images, 34 (SIBGRAPI) |
Conference Location | Gramado, RS, Brazil (virtual) |
Date | 18-22 Oct. 2021 |
Publisher | Sociedade Brasileira de Computação |
Publisher City | Porto Alegre |
Book Title | Proceedings |
Tertiary Type | Master'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 Stage | completed |
Transferable | 1 |
Keywords | Computing computer vision estimation theory pattern recognition |
Abstract | Modern 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. |
Arrangement | urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Partial Least Squares:... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPEW34M/45CTEAE |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/45CTEAE |
Language | en |
Target File | Article.pdf |
User Group | arturjordao@dcc.ufmg.br |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/45PQ3RS |
Citing Item List | sid.inpe.br/sibgrapi/2021/11.12.11.46 2 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy 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 |
|