FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213014045> ?p ?o ?g. }

• W4213014045 endingPage "262" @default.
• W4213014045 startingPage "249" @default.
• W4213014045 abstract "Biometric vein recognition using deep learning has shown promising performance recently. However, due to the lack of vein image training data, the performance is greatly limited. Although the use of traditional data augmentation can alleviate this problem to some extent, it can only expand the intra-class samples and is fundamentally limited to the intra-class space, resulting in limited performance improvement. In this paper, we tackle this deep learning data shortage problem by proposing a GAN-based framework that can generate arbitrary-pattern vein images, which can augment the training data with new vein classes. The proposed generation framework consists of three progressive synthetic steps, namely, generation of random vein patterns in the binary space, refinement of the binary vein patterns, and rendering them into grayscale vein images. Moreover, we use the synthetic dataset to pretrain the feature embedding network via unsupervised contrastive learning, which allows learning data augmentation-invariant and instance-separating representations. After that, we further fine-tune the embedding network on the real training data in a supervised manner. Our results show that high-fidelity and diverse vein image samples can be generated to alleviate the problem of data shortage and improve the learning of feature representations for biometric vein verification." @default.
• W4213014045 created "2022-02-24" @default.
• W4213014045 creator A5005598259 @default.
• W4213014045 creator A5015022081 @default.
• W4213014045 creator A5038133707 @default.
• W4213014045 creator A5064884455 @default.
• W4213014045 creator A5070970751 @default.
• W4213014045 date "2022-04-01" @default.
• W4213014045 modified "2023-10-06" @default.
• W4213014045 title "GAN-Based Inter-Class Sample Generation for Contrastive Learning of Vein Image Representations" @default.
• W4213014045 cites W1969363409 @default.
• W4213014045 cites W1991620112 @default.
• W4213014045 cites W2004617923 @default.
• W4213014045 cites W2058362416 @default.
• W4213014045 cites W2071450451 @default.
• W4213014045 cites W2083801119 @default.
• W4213014045 cites W2102780391 @default.
• W4213014045 cites W2118323481 @default.
• W4213014045 cites W2119416456 @default.
• W4213014045 cites W2138621090 @default.
• W4213014045 cites W2144796873 @default.
• W4213014045 cites W2194775991 @default.
• W4213014045 cites W2328254514 @default.
• W4213014045 cites W2598954556 @default.
• W4213014045 cites W2599632008 @default.
• W4213014045 cites W2606063865 @default.
• W4213014045 cites W2624181600 @default.
• W4213014045 cites W2736199230 @default.
• W4213014045 cites W2791437400 @default.
• W4213014045 cites W2793410607 @default.
• W4213014045 cites W2798991696 @default.
• W4213014045 cites W2811014381 @default.
• W4213014045 cites W2884114979 @default.
• W4213014045 cites W2903419854 @default.
• W4213014045 cites W2915817060 @default.
• W4213014045 cites W2917172368 @default.
• W4213014045 cites W2919938126 @default.
• W4213014045 cites W2938788221 @default.
• W4213014045 cites W2940927497 @default.
• W4213014045 cites W2945197573 @default.
• W4213014045 cites W2946595465 @default.
• W4213014045 cites W2948212638 @default.
• W4213014045 cites W2952056941 @default.
• W4213014045 cites W2952526090 @default.
• W4213014045 cites W2955256527 @default.
• W4213014045 cites W2958587321 @default.
• W4213014045 cites W2962793481 @default.
• W4213014045 cites W2962898354 @default.
• W4213014045 cites W2963073614 @default.
• W4213014045 cites W2963890275 @default.
• W4213014045 cites W2984049105 @default.
• W4213014045 cites W2996162755 @default.
• W4213014045 cites W3003465473 @default.
• W4213014045 cites W3005370840 @default.
• W4213014045 cites W3025751871 @default.
• W4213014045 cites W3034256998 @default.
• W4213014045 cites W3034303554 @default.
• W4213014045 cites W3035524453 @default.
• W4213014045 cites W3049342961 @default.
• W4213014045 cites W3092623934 @default.
• W4213014045 cites W3093656966 @default.
• W4213014045 cites W3099206234 @default.
• W4213014045 cites W3118857593 @default.
• W4213014045 cites W3119247023 @default.
• W4213014045 cites W3126171091 @default.
• W4213014045 cites W3132400026 @default.
• W4213014045 cites W3134449933 @default.
• W4213014045 cites W3156765634 @default.
• W4213014045 cites W3159177986 @default.
• W4213014045 cites W4240805545 @default.
• W4213014045 cites W4246794637 @default.
• W4213014045 cites W4251287167 @default.
• W4213014045 doi "https://doi.org/10.1109/tbiom.2022.3152345" @default.
• W4213014045 hasPublicationYear "2022" @default.
• W4213014045 type Work @default.
• W4213014045 citedByCount "1" @default.
• W4213014045 countsByYear W42130140452023 @default.
• W4213014045 crossrefType "journal-article" @default.
• W4213014045 hasAuthorship W4213014045A5005598259 @default.
• W4213014045 hasAuthorship W4213014045A5015022081 @default.
• W4213014045 hasAuthorship W4213014045A5038133707 @default.
• W4213014045 hasAuthorship W4213014045A5064884455 @default.
• W4213014045 hasAuthorship W4213014045A5070970751 @default.
• W4213014045 hasConcept C108583219 @default.
• W4213014045 hasConcept C12267149 @default.
• W4213014045 hasConcept C153180895 @default.
• W4213014045 hasConcept C154945302 @default.
• W4213014045 hasConcept C184297639 @default.
• W4213014045 hasConcept C205711294 @default.
• W4213014045 hasConcept C41008148 @default.
• W4213014045 hasConcept C41608201 @default.
• W4213014045 hasConcept C66905080 @default.
• W4213014045 hasConcept C83665646 @default.
• W4213014045 hasConceptScore W4213014045C108583219 @default.
• W4213014045 hasConceptScore W4213014045C12267149 @default.
• W4213014045 hasConceptScore W4213014045C153180895 @default.
• W4213014045 hasConceptScore W4213014045C154945302 @default.
• W4213014045 hasConceptScore W4213014045C184297639 @default.

• next