Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216572446> ?p ?o ?g. }
- W3216572446 abstract "Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation provide equal and unbiased performance across subgroups. However, can seemingly unbiased pre-trained model become biased when input data undergoes certain distortions? For the first time, we attempt to answer this question in the context of face recognition. We provide a systematic analysis to evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions across different gender and race subgroups. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups." @default.
- W3216572446 created "2021-12-06" @default.
- W3216572446 creator A5009237168 @default.
- W3216572446 creator A5011779957 @default.
- W3216572446 creator A5030169316 @default.
- W3216572446 creator A5050521702 @default.
- W3216572446 date "2021-10-01" @default.
- W3216572446 modified "2023-09-26" @default.
- W3216572446 title "Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models" @default.
- W3216572446 cites W1982471090 @default.
- W3216572446 cites W2050482109 @default.
- W3216572446 cites W2100960835 @default.
- W3216572446 cites W2194775991 @default.
- W3216572446 cites W2741143921 @default.
- W3216572446 cites W2752782242 @default.
- W3216572446 cites W2755255259 @default.
- W3216572446 cites W2788741149 @default.
- W3216572446 cites W2945433212 @default.
- W3216572446 cites W2949386440 @default.
- W3216572446 cites W2963460857 @default.
- W3216572446 cites W2963980515 @default.
- W3216572446 cites W2969985801 @default.
- W3216572446 cites W2982175467 @default.
- W3216572446 cites W2982232682 @default.
- W3216572446 cites W2990751682 @default.
- W3216572446 cites W3010093963 @default.
- W3216572446 cites W3013338555 @default.
- W3216572446 cites W3022744804 @default.
- W3216572446 cites W3034256900 @default.
- W3216572446 cites W3035232573 @default.
- W3216572446 cites W3035570181 @default.
- W3216572446 cites W3035595647 @default.
- W3216572446 cites W3097003645 @default.
- W3216572446 cites W3107096356 @default.
- W3216572446 cites W3120331640 @default.
- W3216572446 cites W3174760001 @default.
- W3216572446 doi "https://doi.org/10.1109/iccvw54120.2021.00422" @default.
- W3216572446 hasPublicationYear "2021" @default.
- W3216572446 type Work @default.
- W3216572446 sameAs 3216572446 @default.
- W3216572446 citedByCount "3" @default.
- W3216572446 countsByYear W32165724462022 @default.
- W3216572446 countsByYear W32165724462023 @default.
- W3216572446 crossrefType "proceedings-article" @default.
- W3216572446 hasAuthorship W3216572446A5009237168 @default.
- W3216572446 hasAuthorship W3216572446A5011779957 @default.
- W3216572446 hasAuthorship W3216572446A5030169316 @default.
- W3216572446 hasAuthorship W3216572446A5050521702 @default.
- W3216572446 hasConcept C108583219 @default.
- W3216572446 hasConcept C115961682 @default.
- W3216572446 hasConcept C119857082 @default.
- W3216572446 hasConcept C144024400 @default.
- W3216572446 hasConcept C151730666 @default.
- W3216572446 hasConcept C153180895 @default.
- W3216572446 hasConcept C154945302 @default.
- W3216572446 hasConcept C15744967 @default.
- W3216572446 hasConcept C17744445 @default.
- W3216572446 hasConcept C199539241 @default.
- W3216572446 hasConcept C2776359362 @default.
- W3216572446 hasConcept C2779304628 @default.
- W3216572446 hasConcept C2779343474 @default.
- W3216572446 hasConcept C2780586970 @default.
- W3216572446 hasConcept C31510193 @default.
- W3216572446 hasConcept C36289849 @default.
- W3216572446 hasConcept C41008148 @default.
- W3216572446 hasConcept C77805123 @default.
- W3216572446 hasConcept C86803240 @default.
- W3216572446 hasConcept C94625758 @default.
- W3216572446 hasConceptScore W3216572446C108583219 @default.
- W3216572446 hasConceptScore W3216572446C115961682 @default.
- W3216572446 hasConceptScore W3216572446C119857082 @default.
- W3216572446 hasConceptScore W3216572446C144024400 @default.
- W3216572446 hasConceptScore W3216572446C151730666 @default.
- W3216572446 hasConceptScore W3216572446C153180895 @default.
- W3216572446 hasConceptScore W3216572446C154945302 @default.
- W3216572446 hasConceptScore W3216572446C15744967 @default.
- W3216572446 hasConceptScore W3216572446C17744445 @default.
- W3216572446 hasConceptScore W3216572446C199539241 @default.
- W3216572446 hasConceptScore W3216572446C2776359362 @default.
- W3216572446 hasConceptScore W3216572446C2779304628 @default.
- W3216572446 hasConceptScore W3216572446C2779343474 @default.
- W3216572446 hasConceptScore W3216572446C2780586970 @default.
- W3216572446 hasConceptScore W3216572446C31510193 @default.
- W3216572446 hasConceptScore W3216572446C36289849 @default.
- W3216572446 hasConceptScore W3216572446C41008148 @default.
- W3216572446 hasConceptScore W3216572446C77805123 @default.
- W3216572446 hasConceptScore W3216572446C86803240 @default.
- W3216572446 hasConceptScore W3216572446C94625758 @default.
- W3216572446 hasLocation W32165724461 @default.
- W3216572446 hasOpenAccess W3216572446 @default.
- W3216572446 hasPrimaryLocation W32165724461 @default.
- W3216572446 hasRelatedWork W2004976700 @default.
- W3216572446 hasRelatedWork W2017517155 @default.
- W3216572446 hasRelatedWork W2060029454 @default.
- W3216572446 hasRelatedWork W2100085003 @default.
- W3216572446 hasRelatedWork W2136485282 @default.
- W3216572446 hasRelatedWork W2347601237 @default.
- W3216572446 hasRelatedWork W2353697322 @default.
- W3216572446 hasRelatedWork W2897995864 @default.
- W3216572446 hasRelatedWork W2987988558 @default.