FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3040291497> ?p ?o ?g. }

• W3040291497 endingPage "420" @default.
• W3040291497 startingPage "410" @default.
• W3040291497 abstract "Modern face recognition systems extract face representations using deep neural networks (DNNs) and give excellent identification and verification results, when tested on high resolution (HR) images. However, the performance of such an algorithm degrades significantly for low resolution (LR) images. A straight forward solution could be to train a DNN, using simultaneously, high and low resolution face images. This approach yields a definite improvement at lower resolutions but suffers a performance degradation for high resolution images. To overcome this shortcoming, we propose to train a network using both HR and LR images under the guidance of a fixed network, pretrained on HR face images. The guidance is provided by minimising the KL-divergence between the output Softmax probabilities of the pretrained (i.e., Teacher) and trainable (i.e., Student) network as well as by sharing the Softmax weights between the two networks. The resulting solution is tested on down-sampled images from FaceScrub and MegaFace datasets and shows a consistent performance improvement across various resolutions. We also tested our proposed solution on standard LR benchmarks such as TinyFace and SCFace. Our algorithm consistently outperforms the state-of-the-art methods on these datasets, confirming the effectiveness and merits of the proposed method." @default.
• W3040291497 created "2020-07-10" @default.
• W3040291497 creator A5025299678 @default.
• W3040291497 creator A5028209738 @default.
• W3040291497 creator A5041931769 @default.
• W3040291497 creator A5049721432 @default.
• W3040291497 creator A5055524671 @default.
• W3040291497 creator A5087389513 @default.
• W3040291497 creator A5087909247 @default.
• W3040291497 date "2020-10-01" @default.
• W3040291497 modified "2023-10-06" @default.
• W3040291497 title "Resolution Invariant Face Recognition Using a Distillation Approach" @default.
• W3040291497 cites W1892323599 @default.
• W3040291497 cites W1981341515 @default.
• W3040291497 cites W1998594584 @default.
• W3040291497 cites W2024922353 @default.
• W3040291497 cites W2047186200 @default.
• W3040291497 cites W2055492845 @default.
• W3040291497 cites W2114380981 @default.
• W3040291497 cites W2126653386 @default.
• W3040291497 cites W2145287260 @default.
• W3040291497 cites W2157285372 @default.
• W3040291497 cites W2163808566 @default.
• W3040291497 cites W2194775991 @default.
• W3040291497 cites W2342967552 @default.
• W3040291497 cites W2548498729 @default.
• W3040291497 cites W2554268477 @default.
• W3040291497 cites W2580365077 @default.
• W3040291497 cites W2620727906 @default.
• W3040291497 cites W2679426462 @default.
• W3040291497 cites W2747898905 @default.
• W3040291497 cites W2751503239 @default.
• W3040291497 cites W2752042386 @default.
• W3040291497 cites W2770121394 @default.
• W3040291497 cites W2792481260 @default.
• W3040291497 cites W2890129614 @default.
• W3040291497 cites W2911315155 @default.
• W3040291497 cites W2911796133 @default.
• W3040291497 cites W2940110727 @default.
• W3040291497 cites W2962898354 @default.
• W3040291497 cites W2963466847 @default.
• W3040291497 cites W2963566548 @default.
• W3040291497 cites W2963671154 @default.
• W3040291497 cites W2963789946 @default.
• W3040291497 cites W2964167901 @default.
• W3040291497 cites W2969703002 @default.
• W3040291497 cites W2969985801 @default.
• W3040291497 cites W2984516931 @default.
• W3040291497 cites W2995802584 @default.
• W3040291497 cites W3099206234 @default.
• W3040291497 cites W3101998545 @default.
• W3040291497 doi "https://doi.org/10.1109/tbiom.2020.3007356" @default.
• W3040291497 hasPublicationYear "2020" @default.
• W3040291497 type Work @default.
• W3040291497 sameAs 3040291497 @default.
• W3040291497 citedByCount "22" @default.
• W3040291497 countsByYear W30402914972020 @default.
• W3040291497 countsByYear W30402914972021 @default.
• W3040291497 countsByYear W30402914972022 @default.
• W3040291497 countsByYear W30402914972023 @default.
• W3040291497 crossrefType "journal-article" @default.
• W3040291497 hasAuthorship W3040291497A5025299678 @default.
• W3040291497 hasAuthorship W3040291497A5028209738 @default.
• W3040291497 hasAuthorship W3040291497A5041931769 @default.
• W3040291497 hasAuthorship W3040291497A5049721432 @default.
• W3040291497 hasAuthorship W3040291497A5055524671 @default.
• W3040291497 hasAuthorship W3040291497A5087389513 @default.
• W3040291497 hasAuthorship W3040291497A5087909247 @default.
• W3040291497 hasBestOaLocation W30402914972 @default.
• W3040291497 hasConcept C138268822 @default.
• W3040291497 hasConcept C144024400 @default.
• W3040291497 hasConcept C153180895 @default.
• W3040291497 hasConcept C154945302 @default.
• W3040291497 hasConcept C188441871 @default.
• W3040291497 hasConcept C190470478 @default.
• W3040291497 hasConcept C2779304628 @default.
• W3040291497 hasConcept C31510193 @default.
• W3040291497 hasConcept C31972630 @default.
• W3040291497 hasConcept C33923547 @default.
• W3040291497 hasConcept C36289849 @default.
• W3040291497 hasConcept C37914503 @default.
• W3040291497 hasConcept C41008148 @default.
• W3040291497 hasConcept C50644808 @default.
• W3040291497 hasConceptScore W3040291497C138268822 @default.
• W3040291497 hasConceptScore W3040291497C144024400 @default.
• W3040291497 hasConceptScore W3040291497C153180895 @default.
• W3040291497 hasConceptScore W3040291497C154945302 @default.
• W3040291497 hasConceptScore W3040291497C188441871 @default.
• W3040291497 hasConceptScore W3040291497C190470478 @default.
• W3040291497 hasConceptScore W3040291497C2779304628 @default.
• W3040291497 hasConceptScore W3040291497C31510193 @default.
• W3040291497 hasConceptScore W3040291497C31972630 @default.
• W3040291497 hasConceptScore W3040291497C33923547 @default.
• W3040291497 hasConceptScore W3040291497C36289849 @default.
• W3040291497 hasConceptScore W3040291497C37914503 @default.
• W3040291497 hasConceptScore W3040291497C41008148 @default.
• W3040291497 hasConceptScore W3040291497C50644808 @default.
• W3040291497 hasFunder F4320334627 @default.

• next