Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/47JU8TS
Repositorysid.inpe.br/sibgrapi/2022/09.10.20.10
Last Update2022:09.15.00.32.28 (UTC) mateus.miranda@inpe.br
Metadata Repositorysid.inpe.br/sibgrapi/2022/09.10.20.10.21
Metadata Last Update2023:05.23.04.20.42 (UTC) administrator
DOI10.1109/SIBGRAPI55357.2022.9991746
Citation KeyMirandaSiSaSaKöAl:2022:HiReDa
TitleA High-Spatial Resolution Dataset and Few-shot Deep Learning Benchmark for Image Classification
FormatOn-line
Year2022
Access Date2024, May 02
Number of Files1
Size25680 KiB
2. Context
Author1 Miranda, Mateus de Souza
2 Silva, Lucas Fernando Alvarenga e
3 Santos, Samuel Felipe dos
4 Santiago Júnior, Valdivino Alexandre de
5 Körting, Thales Sehn
6 Almeida, Jurandy
Resume Identifier1  
2  
3  
4 8JMKD3MGP5W/3C9JJB5
Group1 CAP-COMP-DIPGR-INPE-MCTI-GOV-BR 
2  
3  
4 COPDT-CGIP-INPE-MCTI-GOV-BR 
5 DIOTG-CGCT-INPE-MCTI-GOV-BR 
Affiliation1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 Universidade Federal de São Paulo (UNIFESP)
3 Universidade Federal de São Paulo (UNIFESP)
4 Instituto Nacional de Pesquisas Espaciais (INPE)
5 Instituto Nacional de Pesquisas Espaciais (INPE)
6 Universidade Federal de São Carlos (UFSCar)
e-Mail Addressmateus.miranda@inpe.br
Conference NameConference on Graphics, Patterns and Images, 35 (SIBGRAPI)
Conference LocationNatal, RN
Date24-27 Oct. 2022
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2022-09-10 20:11:24 :: mateus.miranda@inpe.br -> administrator :: 2022
2022-09-11 01:50:18 :: administrator -> mateus.miranda@inpe.br :: 2022
2022-09-15 00:32:29 :: mateus.miranda@inpe.br -> administrator :: 2022
2023-05-23 04:20:42 :: administrator -> :: 2022
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
KeywordsDataset. Few-shot. Deep Learning. Cerrado. Remote Sensing
AbstractThis paper presents a high-spatial-resolution dataset with remote sensing images of the Brazilian Cerrado for land use and land cover classification. The Biome Cerrado Dataset (Cerra- Data) is a large database created from 150 scenes of the CBERS- 4A satellite. Images were created by merging the near-infrared, green, and blue bands. Moreover, pan-sharpening was performed between all the scenes and their respective panchromatic bands, resulting in a final spatial resolution of two meters. A total of 2.5 million tiles of 256x256 pixels were derived from these scenes. From this total, 50 thousand tiles were labeled. We also conducted a few-shot learning experiment considering a training set with only 100 samples, 11 deep neural networks (DNNs), and two traditional machine learning (ML) algorithms, i.e., support vector machine (SVM) and random forest (RF). Results show that the DNN DenseNet-161 was the best model but its performance can be improved if it is used only as a feature extractor, leaving the classification task for the traditional ML algorithms. However, by decreasing the size of the training set, smarter approaches are needed. The labeled subset of CerraData as well as the source code we developed to support this study are available on-line: https://github.com/ai4luc/CerraData-code-data.
Arrangement 1urlib.net > BDMCI > Fonds > Produção pgr ATUAIS > CAP > A High-Spatial Resolution...
Arrangement 2urlib.net > SDLA > Fonds > SIBGRAPI 2022 > A High-Spatial Resolution...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 10/09/2022 17:10 1.6 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/47JU8TS
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/47JU8TS
Languageen
Target Filemiranda_400826.pdf
User Groupmateus.miranda@inpe.br
Visibilityshown
Read Permissionallow from all
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPCW/3F2PHGS
8JMKD3MGPEW34M/495MHJ8
Citing Item Listsid.inpe.br/sibgrapi/2023/05.19.12.10 5
sid.inpe.br/sibgrapi/2022/06.10.21.49 1
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 editor electronicmailaddress holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress readergroup rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume


Close