Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384340969> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4384340969 endingPage "3066" @default.
- W4384340969 startingPage "3066" @default.
- W4384340969 abstract "Bias 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." @default.
- W4384340969 created "2023-07-15" @default.
- W4384340969 creator A5010831226 @default.
- W4384340969 creator A5019656391 @default.
- W4384340969 creator A5081818290 @default.
- W4384340969 creator A5087109375 @default.
- W4384340969 date "2023-07-13" @default.
- W4384340969 modified "2023-10-18" @default.
- W4384340969 title "Assessing Biases through Visual Contexts" @default.
- W4384340969 cites W1787224781 @default.
- W4384340969 cites W2117539524 @default.
- W4384340969 cites W2282821441 @default.
- W4384340969 cites W3003562648 @default.
- W4384340969 cites W3004493409 @default.
- W4384340969 cites W3036562634 @default.
- W4384340969 cites W3102564565 @default.
- W4384340969 cites W3123283725 @default.
- W4384340969 cites W3183198896 @default.
- W4384340969 cites W4280534984 @default.
- W4384340969 cites W4290852327 @default.
- W4384340969 cites W4295768443 @default.
- W4384340969 cites W4312933868 @default.
- W4384340969 doi "https://doi.org/10.3390/electronics12143066" @default.
- W4384340969 hasPublicationYear "2023" @default.
- W4384340969 type Work @default.
- W4384340969 citedByCount "0" @default.
- W4384340969 crossrefType "journal-article" @default.
- W4384340969 hasAuthorship W4384340969A5010831226 @default.
- W4384340969 hasAuthorship W4384340969A5019656391 @default.
- W4384340969 hasAuthorship W4384340969A5081818290 @default.
- W4384340969 hasAuthorship W4384340969A5087109375 @default.
- W4384340969 hasBestOaLocation W43843409691 @default.
- W4384340969 hasConcept C115961682 @default.
- W4384340969 hasConcept C119857082 @default.
- W4384340969 hasConcept C121332964 @default.
- W4384340969 hasConcept C124101348 @default.
- W4384340969 hasConcept C127413603 @default.
- W4384340969 hasConcept C151730666 @default.
- W4384340969 hasConcept C154945302 @default.
- W4384340969 hasConcept C163258240 @default.
- W4384340969 hasConcept C201995342 @default.
- W4384340969 hasConcept C202444582 @default.
- W4384340969 hasConcept C2776436953 @default.
- W4384340969 hasConcept C2779343474 @default.
- W4384340969 hasConcept C2780451532 @default.
- W4384340969 hasConcept C33923547 @default.
- W4384340969 hasConcept C41008148 @default.
- W4384340969 hasConcept C43214815 @default.
- W4384340969 hasConcept C62520636 @default.
- W4384340969 hasConcept C86803240 @default.
- W4384340969 hasConcept C9652623 @default.
- W4384340969 hasConcept C99498987 @default.
- W4384340969 hasConceptScore W4384340969C115961682 @default.
- W4384340969 hasConceptScore W4384340969C119857082 @default.
- W4384340969 hasConceptScore W4384340969C121332964 @default.
- W4384340969 hasConceptScore W4384340969C124101348 @default.
- W4384340969 hasConceptScore W4384340969C127413603 @default.
- W4384340969 hasConceptScore W4384340969C151730666 @default.
- W4384340969 hasConceptScore W4384340969C154945302 @default.
- W4384340969 hasConceptScore W4384340969C163258240 @default.
- W4384340969 hasConceptScore W4384340969C201995342 @default.
- W4384340969 hasConceptScore W4384340969C202444582 @default.
- W4384340969 hasConceptScore W4384340969C2776436953 @default.
- W4384340969 hasConceptScore W4384340969C2779343474 @default.
- W4384340969 hasConceptScore W4384340969C2780451532 @default.
- W4384340969 hasConceptScore W4384340969C33923547 @default.
- W4384340969 hasConceptScore W4384340969C41008148 @default.
- W4384340969 hasConceptScore W4384340969C43214815 @default.
- W4384340969 hasConceptScore W4384340969C62520636 @default.
- W4384340969 hasConceptScore W4384340969C86803240 @default.
- W4384340969 hasConceptScore W4384340969C9652623 @default.
- W4384340969 hasConceptScore W4384340969C99498987 @default.
- W4384340969 hasIssue "14" @default.
- W4384340969 hasLocation W43843409691 @default.
- W4384340969 hasOpenAccess W4384340969 @default.
- W4384340969 hasPrimaryLocation W43843409691 @default.
- W4384340969 hasRelatedWork W2350879319 @default.
- W4384340969 hasRelatedWork W2961085424 @default.
- W4384340969 hasRelatedWork W4285260836 @default.
- W4384340969 hasRelatedWork W4286629047 @default.
- W4384340969 hasRelatedWork W4288754364 @default.
- W4384340969 hasRelatedWork W4306321456 @default.
- W4384340969 hasRelatedWork W4306674287 @default.
- W4384340969 hasRelatedWork W4308734192 @default.
- W4384340969 hasRelatedWork W4312831135 @default.
- W4384340969 hasRelatedWork W4224009465 @default.
- W4384340969 hasVolume "12" @default.
- W4384340969 isParatext "false" @default.
- W4384340969 isRetracted "false" @default.
- W4384340969 workType "article" @default.