Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281384324> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4281384324 abstract "The increasing amount of applications of Artificial Intelligence (AI) has led researchers to study the social impact of these technologies and evaluate their fairness. Unfortunately, current fairness metrics are hard to apply in multi-class multi-demographic classification problems, such as Facial Expression Recognition (FER). We propose a new set of metrics to approach these problems. Of the three metrics proposed, two focus on the representational and stereotypical bias of the dataset, and the third one on the residual bias of the trained model. These metrics combined can potentially be used to study and compare diverse bias mitigation methods. We demonstrate the usefulness of the metrics by applying them to a FER problem based on the popular Affectnet dataset. Like many other datasets for FER, Affectnet is a large Internet-sourced dataset with 291,651 labeled images. Obtaining images from the Internet raises some concerns over the fairness of any system trained on this data and its ability to generalize properly to diverse populations. We first analyze the dataset and some variants, finding substantial racial bias and gender stereotypes. We then extract several subsets with different demographic properties and train a model on each one, observing the amount of residual bias in the different setups. We also provide a second analysis on a different dataset, FER+." @default.
- W4281384324 created "2022-05-25" @default.
- W4281384324 creator A5027737844 @default.
- W4281384324 creator A5048848385 @default.
- W4281384324 creator A5074741708 @default.
- W4281384324 date "2022-05-20" @default.
- W4281384324 modified "2023-10-16" @default.
- W4281384324 title "Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognition" @default.
- W4281384324 doi "https://doi.org/10.48550/arxiv.2205.10049" @default.
- W4281384324 hasPublicationYear "2022" @default.
- W4281384324 type Work @default.
- W4281384324 citedByCount "1" @default.
- W4281384324 countsByYear W42813843242023 @default.
- W4281384324 crossrefType "posted-content" @default.
- W4281384324 hasAuthorship W4281384324A5027737844 @default.
- W4281384324 hasAuthorship W4281384324A5048848385 @default.
- W4281384324 hasAuthorship W4281384324A5074741708 @default.
- W4281384324 hasBestOaLocation W42813843241 @default.
- W4281384324 hasConcept C110875604 @default.
- W4281384324 hasConcept C11413529 @default.
- W4281384324 hasConcept C119857082 @default.
- W4281384324 hasConcept C120665830 @default.
- W4281384324 hasConcept C121332964 @default.
- W4281384324 hasConcept C124101348 @default.
- W4281384324 hasConcept C136764020 @default.
- W4281384324 hasConcept C144024400 @default.
- W4281384324 hasConcept C153180895 @default.
- W4281384324 hasConcept C154945302 @default.
- W4281384324 hasConcept C155512373 @default.
- W4281384324 hasConcept C177264268 @default.
- W4281384324 hasConcept C192209626 @default.
- W4281384324 hasConcept C195704467 @default.
- W4281384324 hasConcept C199360897 @default.
- W4281384324 hasConcept C2777212361 @default.
- W4281384324 hasConcept C2779304628 @default.
- W4281384324 hasConcept C36289849 @default.
- W4281384324 hasConcept C41008148 @default.
- W4281384324 hasConceptScore W4281384324C110875604 @default.
- W4281384324 hasConceptScore W4281384324C11413529 @default.
- W4281384324 hasConceptScore W4281384324C119857082 @default.
- W4281384324 hasConceptScore W4281384324C120665830 @default.
- W4281384324 hasConceptScore W4281384324C121332964 @default.
- W4281384324 hasConceptScore W4281384324C124101348 @default.
- W4281384324 hasConceptScore W4281384324C136764020 @default.
- W4281384324 hasConceptScore W4281384324C144024400 @default.
- W4281384324 hasConceptScore W4281384324C153180895 @default.
- W4281384324 hasConceptScore W4281384324C154945302 @default.
- W4281384324 hasConceptScore W4281384324C155512373 @default.
- W4281384324 hasConceptScore W4281384324C177264268 @default.
- W4281384324 hasConceptScore W4281384324C192209626 @default.
- W4281384324 hasConceptScore W4281384324C195704467 @default.
- W4281384324 hasConceptScore W4281384324C199360897 @default.
- W4281384324 hasConceptScore W4281384324C2777212361 @default.
- W4281384324 hasConceptScore W4281384324C2779304628 @default.
- W4281384324 hasConceptScore W4281384324C36289849 @default.
- W4281384324 hasConceptScore W4281384324C41008148 @default.
- W4281384324 hasLocation W42813843241 @default.
- W4281384324 hasOpenAccess W4281384324 @default.
- W4281384324 hasPrimaryLocation W42813843241 @default.
- W4281384324 hasRelatedWork W1775397219 @default.
- W4281384324 hasRelatedWork W2004976700 @default.
- W4281384324 hasRelatedWork W2060029454 @default.
- W4281384324 hasRelatedWork W2096776307 @default.
- W4281384324 hasRelatedWork W2136485282 @default.
- W4281384324 hasRelatedWork W2347601237 @default.
- W4281384324 hasRelatedWork W2353697322 @default.
- W4281384324 hasRelatedWork W2383164569 @default.
- W4281384324 hasRelatedWork W2897995864 @default.
- W4281384324 hasRelatedWork W4301184459 @default.
- W4281384324 isParatext "false" @default.
- W4281384324 isRetracted "false" @default.
- W4281384324 workType "article" @default.