1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/3U2JCS5 |
Repository | sid.inpe.br/sibgrapi/2019/09.09.17.29 |
Last Update | 2019:09.09.17.29.19 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2019/09.09.17.29.19 |
Metadata Last Update | 2022:06.14.00.09.32 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2019.00040 |
Citation Key | SantosPont:2019:AlLoGl |
Title | Alignment of Local and Global Features from Multiple Layers of Convolutional Neural Network for Image Classification |
Format | On-line |
Year | 2019 |
Access Date | 2024, Apr. 28 |
Number of Files | 1 |
Size | 3424 KiB |
|
2. Context | |
Author | 1 Santos, Fernando Pereira dos 2 Ponti, Moacir Antonelli |
Affiliation | 1 Universidade de São Paulo 2 Universidade de São Paulo |
Editor | Oliveira, Luciano Rebouças de Sarder, Pinaki Lage, Marcos Sadlo, Filip |
e-Mail Address | fernando_persan@usp.br |
Conference Name | Conference on Graphics, Patterns and Images, 32 (SIBGRAPI) |
Conference Location | Rio de Janeiro, RJ, Brazil |
Date | 28-31 Oct. 2019 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full 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 Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | feature learning convolutional networks fusion multiple maps manifold alignment |
Abstract | Convolutional 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 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2019 > Alignment of Local... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Alignment of Local... |
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/3U2JCS5 |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/3U2JCS5 |
Language | en |
Target File | camera_ready_92.pdf |
User Group | fernando_persan@usp.br |
Visibility | shown |
Update Permission | not transferred |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/3UA4FNL 8JMKD3MGPEW34M/3UA4FPS 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2019/10.25.18.30.33 1 sid.inpe.br/banon/2001/03.30.15.38.24 1 |
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 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 | |
|