Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912105508> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2912105508 endingPage "1479" @default.
- W2912105508 startingPage "1464" @default.
- W2912105508 abstract "In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn’t need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFace1, which uses pairs of face images as inputs and maps them to target space so that the L2 norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition." @default.
- W2912105508 created "2019-02-21" @default.
- W2912105508 creator A5002854902 @default.
- W2912105508 creator A5018244700 @default.
- W2912105508 creator A5031537926 @default.
- W2912105508 creator A5067580558 @default.
- W2912105508 creator A5072241102 @default.
- W2912105508 date "2018-12-01" @default.
- W2912105508 modified "2023-09-23" @default.
- W2912105508 title "Small Sample Face Recognition Algorithm based on Novel Siamese Network" @default.
- W2912105508 doi "https://doi.org/10.3745/jips.02.0101" @default.
- W2912105508 hasPublicationYear "2018" @default.
- W2912105508 type Work @default.
- W2912105508 sameAs 2912105508 @default.
- W2912105508 citedByCount "1" @default.
- W2912105508 countsByYear W29121055082021 @default.
- W2912105508 crossrefType "journal-article" @default.
- W2912105508 hasAuthorship W2912105508A5002854902 @default.
- W2912105508 hasAuthorship W2912105508A5018244700 @default.
- W2912105508 hasAuthorship W2912105508A5031537926 @default.
- W2912105508 hasAuthorship W2912105508A5067580558 @default.
- W2912105508 hasAuthorship W2912105508A5072241102 @default.
- W2912105508 hasConcept C111919701 @default.
- W2912105508 hasConcept C11413529 @default.
- W2912105508 hasConcept C14036430 @default.
- W2912105508 hasConcept C144024400 @default.
- W2912105508 hasConcept C153180895 @default.
- W2912105508 hasConcept C154945302 @default.
- W2912105508 hasConcept C185592680 @default.
- W2912105508 hasConcept C198531522 @default.
- W2912105508 hasConcept C2778572836 @default.
- W2912105508 hasConcept C2779304628 @default.
- W2912105508 hasConcept C31510193 @default.
- W2912105508 hasConcept C36289849 @default.
- W2912105508 hasConcept C41008148 @default.
- W2912105508 hasConcept C43617362 @default.
- W2912105508 hasConcept C50644808 @default.
- W2912105508 hasConcept C78458016 @default.
- W2912105508 hasConcept C81363708 @default.
- W2912105508 hasConcept C86803240 @default.
- W2912105508 hasConceptScore W2912105508C111919701 @default.
- W2912105508 hasConceptScore W2912105508C11413529 @default.
- W2912105508 hasConceptScore W2912105508C14036430 @default.
- W2912105508 hasConceptScore W2912105508C144024400 @default.
- W2912105508 hasConceptScore W2912105508C153180895 @default.
- W2912105508 hasConceptScore W2912105508C154945302 @default.
- W2912105508 hasConceptScore W2912105508C185592680 @default.
- W2912105508 hasConceptScore W2912105508C198531522 @default.
- W2912105508 hasConceptScore W2912105508C2778572836 @default.
- W2912105508 hasConceptScore W2912105508C2779304628 @default.
- W2912105508 hasConceptScore W2912105508C31510193 @default.
- W2912105508 hasConceptScore W2912105508C36289849 @default.
- W2912105508 hasConceptScore W2912105508C41008148 @default.
- W2912105508 hasConceptScore W2912105508C43617362 @default.
- W2912105508 hasConceptScore W2912105508C50644808 @default.
- W2912105508 hasConceptScore W2912105508C78458016 @default.
- W2912105508 hasConceptScore W2912105508C81363708 @default.
- W2912105508 hasConceptScore W2912105508C86803240 @default.
- W2912105508 hasIssue "6" @default.
- W2912105508 hasLocation W29121055081 @default.
- W2912105508 hasOpenAccess W2912105508 @default.
- W2912105508 hasPrimaryLocation W29121055081 @default.
- W2912105508 hasRelatedWork W2219193941 @default.
- W2912105508 hasRelatedWork W2586788794 @default.
- W2912105508 hasRelatedWork W2592598587 @default.
- W2912105508 hasRelatedWork W2749853774 @default.
- W2912105508 hasRelatedWork W2766216301 @default.
- W2912105508 hasRelatedWork W2769050002 @default.
- W2912105508 hasRelatedWork W2769296245 @default.
- W2912105508 hasRelatedWork W2774383581 @default.
- W2912105508 hasRelatedWork W2885013404 @default.
- W2912105508 hasRelatedWork W2889780505 @default.
- W2912105508 hasRelatedWork W2922170518 @default.
- W2912105508 hasRelatedWork W2952198537 @default.
- W2912105508 hasRelatedWork W2963713828 @default.
- W2912105508 hasRelatedWork W3039081519 @default.
- W2912105508 hasRelatedWork W3049015794 @default.
- W2912105508 hasRelatedWork W3104899859 @default.
- W2912105508 hasRelatedWork W3157813449 @default.
- W2912105508 hasRelatedWork W3185719004 @default.
- W2912105508 hasRelatedWork W3190346410 @default.
- W2912105508 hasRelatedWork W3118922411 @default.
- W2912105508 hasVolume "14" @default.
- W2912105508 isParatext "false" @default.
- W2912105508 isRetracted "false" @default.
- W2912105508 magId "2912105508" @default.
- W2912105508 workType "article" @default.