Matches in SemOpenAlex for { <https://semopenalex.org/work/W3095903167> ?p ?o ?g. }
- W3095903167 endingPage "1832" @default.
- W3095903167 startingPage "1832" @default.
- W3095903167 abstract "Deep learning-based feature extraction methods and transfer learning have become common approaches in the field of pattern recognition. Deep convolutional neural networks trained using tripled-based loss functions allow for the generation of face embeddings, which can be directly applied to face verification and clustering. Knowledge about the ground truth of face identities might improve the effectiveness of the final classification algorithm; however, it is also possible to use ground truth clusters previously discovered using an unsupervised approach. The aim of this paper is to evaluate the potential improvement of classification results of state-of-the-art supervised classification methods trained with and without ground truth knowledge. In this study, we use two sufficiently large data sets containing more than 200,000 “taken in the wild” images, each with various resolutions, visual quality, and face poses which, in our opinion, guarantee the statistical significance of the results. We examine several clustering and supervised pattern recognition algorithms and find that knowledge about the ground truth has a very small influence on the Fowlkes–Mallows score (FMS) of the classification algorithm. In the case of the classification algorithm that obtained the highest accuracy in our experiment, the FMS improved by only 5.3% (from 0.749 to 0.791) in the first data set and by 6.6% (from 0.652 to 0.718) in the second data set. Our results show that, beside highly secure systems in which face verification is a key component, face identities discovered by unsupervised approaches can be safely used for training supervised classifiers. We also found that the Silhouette Coefficient (SC) of unsupervised clustering is positively correlated with the Adjusted Rand Index, V-measure score, and Fowlkes–Mallows score and, so, we can use the SC as an indicator of clustering performance when the ground truth of face identities is not known. All of these conclusions are important findings for large-scale face verification problems. The reason for this is the fact that skipping the verification of people’s identities before supervised training saves a lot of time and resources." @default.
- W3095903167 created "2020-11-09" @default.
- W3095903167 creator A5026272113 @default.
- W3095903167 creator A5058709988 @default.
- W3095903167 date "2020-11-05" @default.
- W3095903167 modified "2023-09-24" @default.
- W3095903167 title "Comparative Analysis of Supervised and Unsupervised Approaches Applied to Large-Scale “In The Wild” Face Verification" @default.
- W3095903167 cites W1987971958 @default.
- W3095903167 cites W2028695285 @default.
- W3095903167 cites W2030644393 @default.
- W3095903167 cites W2085487226 @default.
- W3095903167 cites W2167197286 @default.
- W3095903167 cites W2295124130 @default.
- W3095903167 cites W2383718281 @default.
- W3095903167 cites W2462685695 @default.
- W3095903167 cites W2601243251 @default.
- W3095903167 cites W2618530766 @default.
- W3095903167 cites W2756114629 @default.
- W3095903167 cites W2799041689 @default.
- W3095903167 cites W2801105195 @default.
- W3095903167 cites W2896154921 @default.
- W3095903167 cites W2897958909 @default.
- W3095903167 cites W2913239513 @default.
- W3095903167 cites W2944724518 @default.
- W3095903167 cites W2948429466 @default.
- W3095903167 cites W2962712507 @default.
- W3095903167 cites W2963537829 @default.
- W3095903167 cites W2966322997 @default.
- W3095903167 cites W2971058209 @default.
- W3095903167 cites W2996499584 @default.
- W3095903167 cites W2996835107 @default.
- W3095903167 cites W2997473924 @default.
- W3095903167 cites W3006533904 @default.
- W3095903167 cites W3014229143 @default.
- W3095903167 cites W3015287558 @default.
- W3095903167 cites W3021314293 @default.
- W3095903167 cites W3031350880 @default.
- W3095903167 cites W3044774336 @default.
- W3095903167 cites W3087973064 @default.
- W3095903167 cites W3101998545 @default.
- W3095903167 cites W4235169531 @default.
- W3095903167 doi "https://doi.org/10.3390/sym12111832" @default.
- W3095903167 hasPublicationYear "2020" @default.
- W3095903167 type Work @default.
- W3095903167 sameAs 3095903167 @default.
- W3095903167 citedByCount "2" @default.
- W3095903167 countsByYear W30959031672022 @default.
- W3095903167 crossrefType "journal-article" @default.
- W3095903167 hasAuthorship W3095903167A5026272113 @default.
- W3095903167 hasAuthorship W3095903167A5058709988 @default.
- W3095903167 hasBestOaLocation W30959031671 @default.
- W3095903167 hasConcept C119857082 @default.
- W3095903167 hasConcept C136389625 @default.
- W3095903167 hasConcept C144024400 @default.
- W3095903167 hasConcept C146849305 @default.
- W3095903167 hasConcept C153180895 @default.
- W3095903167 hasConcept C154945302 @default.
- W3095903167 hasConcept C177264268 @default.
- W3095903167 hasConcept C199360897 @default.
- W3095903167 hasConcept C202444582 @default.
- W3095903167 hasConcept C2779304628 @default.
- W3095903167 hasConcept C31510193 @default.
- W3095903167 hasConcept C33923547 @default.
- W3095903167 hasConcept C36289849 @default.
- W3095903167 hasConcept C41008148 @default.
- W3095903167 hasConcept C50644808 @default.
- W3095903167 hasConcept C73555534 @default.
- W3095903167 hasConcept C8038995 @default.
- W3095903167 hasConcept C81363708 @default.
- W3095903167 hasConcept C9652623 @default.
- W3095903167 hasConceptScore W3095903167C119857082 @default.
- W3095903167 hasConceptScore W3095903167C136389625 @default.
- W3095903167 hasConceptScore W3095903167C144024400 @default.
- W3095903167 hasConceptScore W3095903167C146849305 @default.
- W3095903167 hasConceptScore W3095903167C153180895 @default.
- W3095903167 hasConceptScore W3095903167C154945302 @default.
- W3095903167 hasConceptScore W3095903167C177264268 @default.
- W3095903167 hasConceptScore W3095903167C199360897 @default.
- W3095903167 hasConceptScore W3095903167C202444582 @default.
- W3095903167 hasConceptScore W3095903167C2779304628 @default.
- W3095903167 hasConceptScore W3095903167C31510193 @default.
- W3095903167 hasConceptScore W3095903167C33923547 @default.
- W3095903167 hasConceptScore W3095903167C36289849 @default.
- W3095903167 hasConceptScore W3095903167C41008148 @default.
- W3095903167 hasConceptScore W3095903167C50644808 @default.
- W3095903167 hasConceptScore W3095903167C73555534 @default.
- W3095903167 hasConceptScore W3095903167C8038995 @default.
- W3095903167 hasConceptScore W3095903167C81363708 @default.
- W3095903167 hasConceptScore W3095903167C9652623 @default.
- W3095903167 hasIssue "11" @default.
- W3095903167 hasLocation W30959031671 @default.
- W3095903167 hasLocation W30959031672 @default.
- W3095903167 hasOpenAccess W3095903167 @default.
- W3095903167 hasPrimaryLocation W30959031671 @default.
- W3095903167 hasRelatedWork W1775397219 @default.
- W3095903167 hasRelatedWork W2347601237 @default.
- W3095903167 hasRelatedWork W2897995864 @default.
- W3095903167 hasRelatedWork W3046775127 @default.