Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/3U2JCS5
Repositorysid.inpe.br/sibgrapi/2019/09.09.17.29
Last Update2019:09.09.17.29.19 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2019/09.09.17.29.19
Metadata Last Update2022:06.14.00.09.32 (UTC) administrator
DOI10.1109/SIBGRAPI.2019.00040
Citation KeySantosPont:2019:AlLoGl
TitleAlignment of Local and Global Features from Multiple Layers of Convolutional Neural Network for Image Classification
FormatOn-line
Year2019
Access Date2024, Apr. 28
Number of Files1
Size3424 KiB
2. Context
Author1 Santos, Fernando Pereira dos
2 Ponti, Moacir Antonelli
Affiliation1 Universidade de São Paulo
2 Universidade de São Paulo
EditorOliveira, Luciano Rebouças de
Sarder, Pinaki
Lage, Marcos
Sadlo, Filip
e-Mail Addressfernando_persan@usp.br
Conference NameConference on Graphics, Patterns and Images, 32 (SIBGRAPI)
Conference LocationRio de Janeiro, RJ, Brazil
Date28-31 Oct. 2019
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2019-09-09 17:29:19 :: fernando_persan@usp.br -> administrator ::
2022-06-14 00:09:32 :: administrator -> fernando_persan@usp.br :: 2019
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsfeature learning
convolutional networks
fusion multiple maps
manifold alignment
AbstractConvolutional networks have been extensively applied to obtain features spaces for classification tasks. Although those achieve high accuracy in many scenarios, typically only the top layers of the network are explored. Hence, a relevant question arises from this fact: are initial layers useful in terms of discriminative ability? In this paper, we leverage the complementary description offered by such first layers. Our method consists of features extraction in multiple layers, followed by feature selection, fusion of feature maps from the different layers, and space alignment. Through an extensive experimentation with different datasets and studying different training strategies, our results show that local information, coming from the first layers, may significantly improve the classification performance when merged with a global descriptor extracted from a top layer of the network. We report different methods for reducing the dimensionality of the local descriptors, and guidelines on how to align them so that to perform fusion. Our study encourages future studies on combining feature maps from multiple layers, which may be relevant in particular for transfer learning scenarios.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2019 > Alignment of Local...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Alignment of Local...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 09/09/2019 14:29 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/3U2JCS5
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/3U2JCS5
Languageen
Target Filecamera_ready_92.pdf
User Groupfernando_persan@usp.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/3UA4FNL
8JMKD3MGPEW34M/3UA4FPS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2019/10.25.18.30.33 1
sid.inpe.br/banon/2001/03.30.15.38.24 1
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
7. Description control
e-Mail (login)fernando_persan@usp.br
update 


Close