Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/49S978P
Repositorysid.inpe.br/sibgrapi/2023/09.22.20.32
Last Update2023:09.22.20.32.41 (UTC) lucasfernando.aes@gmail.com
Metadata Repositorysid.inpe.br/sibgrapi/2023/09.22.20.32.42
Metadata Last Update2023:09.22.20.32.42 (UTC) lucasfernando.aes@gmail.com
Citation KeyAlvarengaeSilvaAlme:2023:OpSeDo
TitleOpen Set Domain Adaptation Methods in Deep Networks for Image Recognition
FormatOn-line
Year2023
Access Date2024, May 05
Number of Files1
Size403 KiB
2. Context
Author1 Alvarenga e Silva, Lucas Fernando
2 Almeida, Jurandy
Affiliation1 Universidade Estadual de Campinas – UNICAMP
2 Universidade Federal de Săo Carlos – UFScar
EditorClua, Esteban Walter Gonzalez
Körting, Thales Sehn
Paulovich, Fernando Vieira
Feris, Rogerio
e-Mail Addresslucas.silva@ic.unicamp.br
Conference NameConference on Graphics, Patterns and Images, 36 (SIBGRAPI)
Conference LocationRio Grande, RS
DateNov. 06-09, 2023
Book TitleProceedings
Tertiary TypeMaster's or Doctoral Work
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordsopen set domain adaptation
unsupervised domain adaptation
domain adaptation
deep learning
AbstractDeep learning (DL) has revolutionized various fields through its remarkable capacity to learn from raw data. However, in uncontrolled environments like in the wild, the performance of these systems might degrade to some extent, especially with unlabeled datasets. Naive approaches train DL models on labeled datasets (source domains) that resemble the unlabeled test dataset (target domain), but nonetheless, this approach may not yield optimal results due to domain and category-shift problems. These issues have been the primary focus of Unsupervised Domain Adaptation (UDA) and Open Set Recognition research areas. To address the domain-shift problem, we introduced the Multi-Source Domain Alignment Layers (MS-DIAL), a structural solution for multi-source UDA. MS-DIAL aligns the source domains and the target domain at various levels of the feature space, individually achieving competitive results comparable to the state-of-the-art, and when combined with other UDA methods, it further enhances transferability by up to 30.64% in relative performance gains. Subsequently, we tackled the demanding setup of Open Set Domain Adaptation (OSDA), where both domain and category-shift issues coexist. Our proposed approach involves dealing with negatives, extracting a high-confidence set of unknown instances, and using them as a hard constraint to refine the classification boundaries of OSDA methods. We assessed our proposal in an extensive set of experiments, which achieved up to 5.8% of absolute performance gains.
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 22/09/2023 17:32 1.6 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/49S978P
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/49S978P
Languageen
Target Filesilva13.pdf
User Grouplucasfernando.aes@gmail.com
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 doi 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 shorttitle sponsor subject tertiarymark type url versiontype volume
7. Description control
e-Mail (login)lucasfernando.aes@gmail.com
update 


Close