FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119247023> ?p ?o ?g. }

• W3119247023 endingPage "114584" @default.
• W3119247023 startingPage "114584" @default.
• W3119247023 abstract "Finger vein recognition (FVR) based on deep learning (DL) has gained rising attention in recent years. However, the performance of FVR is limited by the insufficient amount of finger vein training data and the weak generalization of learned features. To address these limitations and improve the performance, we propose a simple framework by jointly considering intensive data augmentation, loss function design and network architecture selection. Firstly, we propose a simple inter-class data augmentation technique that can double the number of finger vein training classes with new vein patterns via vertical flipping. Then, we combine it with conventional intra-class data augmentation methods to achieve highly diversified expansion, thereby effectively resolving the data shortage problem. In order to enhance the discrimination of deep features, we design a fusion loss by incorporating the classification loss and the metric learning loss. We find that the fusion of these two penalty signals will lead to a good trade-off between the intra-class similarity and inter-class separability, thereby greatly improving the generalization ability of learned features. We also investigate various network architectures for FVR application in terms of performances and model complexities. To examine the reliability and efficiency of our proposed framework, we implement a real-time FVR system to perform end-to-end verification in a near-realworld working condition. In challenging open-set evaluation protocol, extensive experiments conducted on three public finger vein databases and an in-house database confirm the effectiveness of the proposed method." @default.
• W3119247023 created "2021-01-18" @default.
• W3119247023 creator A5005598259 @default.
• W3119247023 creator A5008554311 @default.
• W3119247023 creator A5015022081 @default.
• W3119247023 creator A5038133707 @default.
• W3119247023 creator A5045062901 @default.
• W3119247023 creator A5064884455 @default.
• W3119247023 date "2021-06-01" @default.
• W3119247023 modified "2023-09-29" @default.
• W3119247023 title "Fusion loss and inter-class data augmentation for deep finger vein feature learning" @default.
• W3119247023 cites W1966602166 @default.
• W3119247023 cites W1969363409 @default.
• W3119247023 cites W1970490745 @default.
• W3119247023 cites W1991620112 @default.
• W3119247023 cites W1997175872 @default.
• W3119247023 cites W2004617923 @default.
• W3119247023 cites W2023631753 @default.
• W3119247023 cites W2039536345 @default.
• W3119247023 cites W2053009119 @default.
• W3119247023 cites W2058362416 @default.
• W3119247023 cites W2097418325 @default.
• W3119247023 cites W2102780391 @default.
• W3119247023 cites W2122790104 @default.
• W3119247023 cites W2138460174 @default.
• W3119247023 cites W2328254514 @default.
• W3119247023 cites W2598954556 @default.
• W3119247023 cites W2599632008 @default.
• W3119247023 cites W2600360414 @default.
• W3119247023 cites W2624181600 @default.
• W3119247023 cites W2791437400 @default.
• W3119247023 cites W2793410607 @default.
• W3119247023 cites W2811014381 @default.
• W3119247023 cites W2884114979 @default.
• W3119247023 cites W2888322626 @default.
• W3119247023 cites W2919938126 @default.
• W3119247023 cites W2921209596 @default.
• W3119247023 cites W2945197573 @default.
• W3119247023 cites W2954996726 @default.
• W3119247023 cites W2955256527 @default.
• W3119247023 cites W2958587321 @default.
• W3119247023 cites W2996162755 @default.
• W3119247023 cites W3004478798 @default.
• W3119247023 cites W3005370840 @default.
• W3119247023 cites W3011835379 @default.
• W3119247023 cites W4246794637 @default.
• W3119247023 doi "https://doi.org/10.1016/j.eswa.2021.114584" @default.
• W3119247023 hasPublicationYear "2021" @default.
• W3119247023 type Work @default.
• W3119247023 sameAs 3119247023 @default.
• W3119247023 citedByCount "12" @default.
• W3119247023 countsByYear W31192470232021 @default.
• W3119247023 countsByYear W31192470232022 @default.
• W3119247023 countsByYear W31192470232023 @default.
• W3119247023 crossrefType "journal-article" @default.
• W3119247023 hasAuthorship W3119247023A5005598259 @default.
• W3119247023 hasAuthorship W3119247023A5008554311 @default.
• W3119247023 hasAuthorship W3119247023A5015022081 @default.
• W3119247023 hasAuthorship W3119247023A5038133707 @default.
• W3119247023 hasAuthorship W3119247023A5045062901 @default.
• W3119247023 hasAuthorship W3119247023A5064884455 @default.
• W3119247023 hasConcept C103278499 @default.
• W3119247023 hasConcept C108583219 @default.
• W3119247023 hasConcept C115961682 @default.
• W3119247023 hasConcept C119857082 @default.
• W3119247023 hasConcept C124101348 @default.
• W3119247023 hasConcept C134306372 @default.
• W3119247023 hasConcept C154945302 @default.
• W3119247023 hasConcept C162324750 @default.
• W3119247023 hasConcept C176217482 @default.
• W3119247023 hasConcept C177148314 @default.
• W3119247023 hasConcept C21547014 @default.
• W3119247023 hasConcept C2777212361 @default.
• W3119247023 hasConcept C33923547 @default.
• W3119247023 hasConcept C41008148 @default.
• W3119247023 hasConceptScore W3119247023C103278499 @default.
• W3119247023 hasConceptScore W3119247023C108583219 @default.
• W3119247023 hasConceptScore W3119247023C115961682 @default.
• W3119247023 hasConceptScore W3119247023C119857082 @default.
• W3119247023 hasConceptScore W3119247023C124101348 @default.
• W3119247023 hasConceptScore W3119247023C134306372 @default.
• W3119247023 hasConceptScore W3119247023C154945302 @default.
• W3119247023 hasConceptScore W3119247023C162324750 @default.
• W3119247023 hasConceptScore W3119247023C176217482 @default.
• W3119247023 hasConceptScore W3119247023C177148314 @default.
• W3119247023 hasConceptScore W3119247023C21547014 @default.
• W3119247023 hasConceptScore W3119247023C2777212361 @default.
• W3119247023 hasConceptScore W3119247023C33923547 @default.
• W3119247023 hasConceptScore W3119247023C41008148 @default.
• W3119247023 hasLocation W31192470231 @default.
• W3119247023 hasOpenAccess W3119247023 @default.
• W3119247023 hasPrimaryLocation W31192470231 @default.
• W3119247023 hasRelatedWork W2922457425 @default.
• W3119247023 hasRelatedWork W3014300295 @default.
• W3119247023 hasRelatedWork W3164822677 @default.
• W3119247023 hasRelatedWork W4223943233 @default.
• W3119247023 hasRelatedWork W4225161397 @default.
• W3119247023 hasRelatedWork W4250304930 @default.

• next