FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892045525> ?p ?o ?g. }

• W2892045525 endingPage "452" @default.
• W2892045525 startingPage "441" @default.
• W2892045525 abstract "Recently, some generative adversarial network (GAN)-based super-resolution (SR) methods have progressed to the point where they can produce photo-realistic natural images by using a generator (G) and discriminator (D) adversarial scheme. However, vanilla GAN-based SR methods cannot achieve good reconstruction and perceptual fidelity on real-world facial images at the same time. Because of D loss, them are hard to converge stably, which may cause the model collapse. In this paper, we present an Enhanced Discriminative Generative Adversarial Network (EDGAN) for SR facial recognition to achieve better reconstruction and perceptual fidelities. First, we discover that a versatile D boosts the adversarial framework to a preferable Nash equilibrium. Then, we design the D via dense connections, which brings more stable adversarial loss. Furthermore, a novel perceptual loss function, by reusing the intermediate features of D, is used to eliminate the gradient vanishing problem of Gs. To our knowledge, this is the first framework to focus on improving the performance of the D. Quantitatively, experimental results show the advantages of EDGAN on two widely used facial image databases against the state-of-the-art methods with different terms. EDGAN performs sharper and realistic results on real-world facial images with large pose and illumination variations than its competitors." @default.
• W2892045525 created "2018-09-27" @default.
• W2892045525 creator A5001831755 @default.
• W2892045525 creator A5007082864 @default.
• W2892045525 creator A5015807909 @default.
• W2892045525 creator A5054275925 @default.
• W2892045525 creator A5058154161 @default.
• W2892045525 creator A5069622043 @default.
• W2892045525 creator A5089404454 @default.
• W2892045525 date "2018-01-01" @default.
• W2892045525 modified "2023-09-26" @default.
• W2892045525 title "Enhanced Discriminative Generative Adversarial Network for Face Super-Resolution" @default.
• W2892045525 cites W1834627138 @default.
• W2892045525 cites W2046119925 @default.
• W2892045525 cites W2141983208 @default.
• W2892045525 cites W2194775991 @default.
• W2892045525 cites W2242218935 @default.
• W2892045525 cites W2331128040 @default.
• W2892045525 cites W2507235960 @default.
• W2892045525 cites W2593414223 @default.
• W2892045525 cites W2740535357 @default.
• W2892045525 cites W2780544323 @default.
• W2892045525 cites W2963186101 @default.
• W2892045525 cites W2963372104 @default.
• W2892045525 cites W2963446712 @default.
• W2892045525 cites W2963470893 @default.
• W2892045525 cites W2963583792 @default.
• W2892045525 cites W2964101377 @default.
• W2892045525 cites W54257720 @default.
• W2892045525 doi "https://doi.org/10.1007/978-3-030-00767-6_41" @default.
• W2892045525 hasPublicationYear "2018" @default.
• W2892045525 type Work @default.
• W2892045525 sameAs 2892045525 @default.
• W2892045525 citedByCount "11" @default.
• W2892045525 countsByYear W28920455252019 @default.
• W2892045525 countsByYear W28920455252020 @default.
• W2892045525 countsByYear W28920455252021 @default.
• W2892045525 countsByYear W28920455252022 @default.
• W2892045525 countsByYear W28920455252023 @default.
• W2892045525 crossrefType "book-chapter" @default.
• W2892045525 hasAuthorship W2892045525A5001831755 @default.
• W2892045525 hasAuthorship W2892045525A5007082864 @default.
• W2892045525 hasAuthorship W2892045525A5015807909 @default.
• W2892045525 hasAuthorship W2892045525A5054275925 @default.
• W2892045525 hasAuthorship W2892045525A5058154161 @default.
• W2892045525 hasAuthorship W2892045525A5069622043 @default.
• W2892045525 hasAuthorship W2892045525A5089404454 @default.
• W2892045525 hasConcept C115961682 @default.
• W2892045525 hasConcept C121332964 @default.
• W2892045525 hasConcept C144024400 @default.
• W2892045525 hasConcept C153180895 @default.
• W2892045525 hasConcept C154945302 @default.
• W2892045525 hasConcept C163258240 @default.
• W2892045525 hasConcept C2779304628 @default.
• W2892045525 hasConcept C2779803651 @default.
• W2892045525 hasConcept C2780992000 @default.
• W2892045525 hasConcept C2988773926 @default.
• W2892045525 hasConcept C31972630 @default.
• W2892045525 hasConcept C36289849 @default.
• W2892045525 hasConcept C37736160 @default.
• W2892045525 hasConcept C39890363 @default.
• W2892045525 hasConcept C41008148 @default.
• W2892045525 hasConcept C62520636 @default.
• W2892045525 hasConcept C76155785 @default.
• W2892045525 hasConcept C94915269 @default.
• W2892045525 hasConcept C97931131 @default.
• W2892045525 hasConceptScore W2892045525C115961682 @default.
• W2892045525 hasConceptScore W2892045525C121332964 @default.
• W2892045525 hasConceptScore W2892045525C144024400 @default.
• W2892045525 hasConceptScore W2892045525C153180895 @default.
• W2892045525 hasConceptScore W2892045525C154945302 @default.
• W2892045525 hasConceptScore W2892045525C163258240 @default.
• W2892045525 hasConceptScore W2892045525C2779304628 @default.
• W2892045525 hasConceptScore W2892045525C2779803651 @default.
• W2892045525 hasConceptScore W2892045525C2780992000 @default.
• W2892045525 hasConceptScore W2892045525C2988773926 @default.
• W2892045525 hasConceptScore W2892045525C31972630 @default.
• W2892045525 hasConceptScore W2892045525C36289849 @default.
• W2892045525 hasConceptScore W2892045525C37736160 @default.
• W2892045525 hasConceptScore W2892045525C39890363 @default.
• W2892045525 hasConceptScore W2892045525C41008148 @default.
• W2892045525 hasConceptScore W2892045525C62520636 @default.
• W2892045525 hasConceptScore W2892045525C76155785 @default.
• W2892045525 hasConceptScore W2892045525C94915269 @default.
• W2892045525 hasConceptScore W2892045525C97931131 @default.
• W2892045525 hasLocation W28920455251 @default.
• W2892045525 hasOpenAccess W2892045525 @default.
• W2892045525 hasPrimaryLocation W28920455251 @default.
• W2892045525 hasRelatedWork W2914998939 @default.
• W2892045525 hasRelatedWork W2952936466 @default.
• W2892045525 hasRelatedWork W3003183197 @default.
• W2892045525 hasRelatedWork W3005996785 @default.
• W2892045525 hasRelatedWork W3208312582 @default.
• W2892045525 hasRelatedWork W4226067002 @default.
• W2892045525 hasRelatedWork W4288624664 @default.
• W2892045525 hasRelatedWork W4306789193 @default.
• W2892045525 hasRelatedWork W4309960897 @default.
• W2892045525 hasRelatedWork W4328029048 @default.

• next