Show simple item record

dc.contributor.authorArias Duart, Anna
dc.contributor.authorGiménez Ábalos, Víctor
dc.contributor.authorCortés García, Claudio Ulises
dc.contributor.authorGarcia Gasulla, Dario
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2023-10-05T09:59:02Z
dc.date.available2023-10-05T09:59:02Z
dc.date.issued2023-07
dc.identifier.citationArias, A. [et al.]. Assessing biases through visual contexts. "Electronics (Switzerland)", Juliol 2023, vol. 12, núm. 14, article 3066.
dc.identifier.issn2079-9292
dc.identifier.urihttp://hdl.handle.net/2117/394659
dc.description.abstractBias detection in the computer vision field is a necessary task, to achieve fair models. These biases are usually due to undesirable correlations present in the data and learned by the model. Although explainability can be a way to gain insights into model behavior, reviewing explanations is not straightforward. This work proposes a methodology to analyze the model biases without using explainability. By doing so, we reduce the potential noise arising from explainability methods, and we minimize human noise during the analysis of explanations. The proposed methodology combines images of the original distribution with images of potential context biases and analyzes the effect produced in the model’s output. For this work, we first presented and released three new datasets generated by diffusion models. Next, we used the proposed methodology to analyze the context impact on the model’s prediction. Finally, we verified the reliability of the proposed methodology and the consistency of its results. We hope this tool will help practitioners to detect and mitigate potential biases, allowing them to obtain more reliable models.
dc.description.sponsorshipThis work received funding from the European Union’s H2020-INFRAIA-2019-1 program under the Grant Agreement n.871042 (SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics) and from the HORIZON-INFRA-2021-DEV-02 program under the Grant Agreement n.101079043 (SoBigData RI Preparatory Phase Project). Additionally, this work was supported by the Departament de Recerca i Universitats of the Generalitat de Catalunya, under the Industrial Doctorate Grant DI 2018-100.
dc.format.extent18 p.
dc.language.isoeng
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Infografia
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshComputer vision
dc.subject.lcshThree-dimensional imaging
dc.subject.otherBias detection
dc.subject.otherMosaics
dc.subject.otherDiffusion models
dc.subject.otherBiased dataset
dc.subject.otherShortcuts
dc.subject.otherContext biases
dc.titleAssessing biases through visual contexts
dc.typeArticle
dc.subject.lemacVisió per ordinador
dc.subject.lemacImatgeria tridimensional
dc.contributor.groupUniversitat Politècnica de Catalunya. IDEAI-UPC - Intelligent Data sciEnce and Artificial Intelligence Research Group
dc.identifier.doi10.3390/electronics12143066
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.mdpi.com/2079-9292/12/14/3066
dc.rights.accessOpen Access
local.identifier.drac37019318
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/H2020/871042/EU/SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics/SoBigData-PlusPlus
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/HE/101079043/EU/SoBigData RI Preparatory Phase Project/SoBigData RI PPP
local.citation.authorArias, A.; Giménez, V.; Cortes, U.; Garcia-Gasulla, D.
local.citation.publicationNameElectronics (Switzerland)
local.citation.volume12
local.citation.number14, article 3066


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record