Show simple item record

dc.contributor.authorChuramani, Nikhil
dc.contributor.authorKara, Ozgur
dc.contributor.authorGunes, Hatice
dc.date.accessioned2022-06-06T23:30:35Z
dc.date.available2022-06-06T23:30:35Z
dc.identifier.issn1949-3045
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/337711
dc.description.abstractAs Facial Expression Recognition (FER) systems become integrated into our daily lives, these systems need to prioritise making fair decisions instead of only aiming at higher individual accuracy scores. From surveillance systems, to monitoring the mental and emotional health of individuals, these systems need to balance the accuracy vs fairness trade-off to make decisions that do not unjustly discriminate against specific under-represented demographic groups. Identifying bias as a critical problem in facial analysis systems, different methods have been proposed that aim to mitigate bias both at data and algorithmic levels. In this work, we propose the novel use of Continual Learning (CL), in particular, using Domain-Incremental Learning (Domain-IL) settings, as a potent bias mitigation method to enhance the fairness of FER systems. We compare different non-CL-based and CL-based methods for their performance and fairness scores on expression recognition and Action Unit (AU) detection tasks using two popular benchmarks, the RAF-DB and BP4D datasets, respectively. Our experimental results show that CL-based methods, on average, outperform other popular bias mitigation techniques on both accuracy and fairness metrics.
dc.publisherInstitute of Electrical and Electronics Engineers
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectFairness
dc.subjectContinual Learning
dc.subjectBias Mitigation
dc.subjectAffective Computing
dc.subjectFacial Expression Recognition
dc.subjectFacial Action Units
dc.titleDomain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
dc.typeArticle
dc.publisher.departmentDepartment of Computer Science and Technology
dc.date.updated2022-06-04T11:12:53Z
prism.publicationNameIEEE Transactions on Affective Computing
dc.identifier.doi10.17863/CAM.85120
dcterms.dateAccepted2022-05-22
rioxxterms.versionAM
dc.contributor.orcidChuramani, Nikhil [0000-0001-5926-0091]
dc.contributor.orcidGunes, Hatice [0000-0003-2407-3012]
rioxxterms.typeJournal Article/Review
pubs.funder-project-idEPSRC (2107412)
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/R030782/1)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Societal Challenges (826232)
cam.depositDate2022-06-04
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International