Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/49L85TH
Repositorysid.inpe.br/sibgrapi/2023/08.16.17.04
Last Update2023:08.16.17.04.58 (UTC) crjung@inf.ufrgs.br
Metadata Repositorysid.inpe.br/sibgrapi/2023/08.16.17.04.58
Metadata Last Update2024:02.17.04.05.20 (UTC) administrator
DOI10.1109/SIBGRAPI59091.2023.10347038
Citation KeyAlbuquerque:2023:MuImSe
TitleMultispectral Image Segmentation With Dimensionality Reduction Using Autoencoders
Short TitleMultispectral Image Segmentation With Dimensionality Reduction Using Autoencoders
FormatOn-line
Year2023
Access Date2024, Apr. 27
Number of Files1
Size408 KiB
2. Context
AuthorAlbuquerque, Eliton
AffiliationFederal University of Rio Grande do Sul
EditorClua, Esteban Walter Gonzalez
Körting, Thales Sehn
Paulovich, Fernando Vieira
Feris, Rogerio
e-Mail Addressjeafilho@inf.ufrgs.br
Conference NameConference on Graphics, Patterns and Images, 36 (SIBGRAPI)
Conference LocationRio Grande, RS
DateNov. 06-09, 2023
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2023-08-16 17:04:58 :: crjung@inf.ufrgs.br -> administrator ::
2024-02-17 04:05:20 :: administrator -> crjung@inf.ufrgs.br :: 2023
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordsmultispectral image processing
semantic segmentation
dimensionality reduction
AbstractAutoencoder (AE) implementations through neural networks have achieved impressive results on dimensionality reduction tasks, such as multispectral (MS) imagery compression. Dimensionality reduction algorithms are necessary when dealing with large multispectral datasets, since the data captured by mul- tiple levels of narrow spectral wavelengths causes high processing and storage costs, particularly when such highly dimensional MS data are used as input to deep learning networks. Traditional data compression techniques like Principal Component Analysis (PCA) are popular in remote sensing applications. However, its implementation on MS data may make the data unusable for computer vision (CV) tasks such as image segmentation, especially when applying severe compression. On the other hand, AEs provide great generalization capabilities over complex data, especially when combined with other CV pipelines. For the relevant problem of semantic segmentation, the results are con- siderably degraded when using dimensionality-reduced images with PCA. When using vanilla autoencoders trained with the traditional MSE loss, the segmentation results improve over PCA but are still considerably behind the one obtained with uncompressed data, which indicates a potential domain shift. In this work, we show that training an AE using a combination of the MSE loss and an additional proxy loss based on a pre- trained segmentation module can significantly improve the AE restoration process, alleviating the accuracy drop of semantic segmentation even for strong compression rates. Our code is available at https://github.com/elitonfilho/pca.
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 16/08/2023 14:04 1.6 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/49L85TH
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/49L85TH
Languageen
Target File77_nocopyright.pdf
User Groupcrjung@inf.ufrgs.br
Visibilityshown
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session sponsor subject tertiarymark type url versiontype volume
7. Description control
e-Mail (login)crjung@inf.ufrgs.br
update 


Close