FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3150874721> ?p ?o ?g. }

• W3150874721 abstract "The interest of the deep learning community in image synthesis has grown massively in recent years. Nowadays, deep generative methods, and especially Generative Adversarial Networks (GANs), are leading to state-of-the-art performance, capable of synthesizing images that appear realistic. While the efforts for improving the quality of the generated images are extensive, most attempts still consider the generator part as an uncorroborated black-box. In this paper, we aim to provide a better understanding and design of the image generation process. We interpret existing generators as implicitly relying on sparsity-inspired models. More specifically, we show that generators can be viewed as manifestations of the Convolutional Sparse Coding (CSC) and its Multi-Layered version (ML-CSC) synthesis processes. We leverage this observation by explicitly enforcing a sparsifying regularization on appropriately chosen activation layers in the generator, and demonstrate that this leads to improved image synthesis. Furthermore, we show that the same rationale and benefits apply to generators serving inverse problems, demonstrated on the Deep Image Prior (DIP) method." @default.
• W3150874721 created "2021-04-13" @default.
• W3150874721 creator A5020279598 @default.
• W3150874721 creator A5091239620 @default.
• W3150874721 date "2021-04-01" @default.
• W3150874721 modified "2023-09-27" @default.
• W3150874721 title "Improved Image Generation via Sparse Modeling." @default.
• W3150874721 cites W1551494903 @default.
• W3150874721 cites W1591116419 @default.
• W3150874721 cites W1603508051 @default.
• W3150874721 cites W1901129140 @default.
• W3150874721 cites W1946953458 @default.
• W3150874721 cites W1976709621 @default.
• W3150874721 cites W1978749115 @default.
• W3150874721 cites W2008732654 @default.
• W3150874721 cites W2048878808 @default.
• W3150874721 cites W2056370875 @default.
• W3150874721 cites W2097117768 @default.
• W3150874721 cites W2099471712 @default.
• W3150874721 cites W2117259536 @default.
• W3150874721 cites W2202656999 @default.
• W3150874721 cites W2464641472 @default.
• W3150874721 cites W2523714292 @default.
• W3150874721 cites W2532801510 @default.
• W3150874721 cites W2593414223 @default.
• W3150874721 cites W2613716286 @default.
• W3150874721 cites W2739748921 @default.
• W3150874721 cites W2752693045 @default.
• W3150874721 cites W2766527293 @default.
• W3150874721 cites W2891463463 @default.
• W3150874721 cites W2893749619 @default.
• W3150874721 cites W2906902254 @default.
• W3150874721 cites W2950798207 @default.
• W3150874721 cites W2962770929 @default.
• W3150874721 cites W2962793481 @default.
• W3150874721 cites W2962879692 @default.
• W3150874721 cites W2963197835 @default.
• W3150874721 cites W2963306805 @default.
• W3150874721 cites W2963368219 @default.
• W3150874721 cites W2963373786 @default.
• W3150874721 cites W2963684088 @default.
• W3150874721 cites W2963836885 @default.
• W3150874721 cites W2963981733 @default.
• W3150874721 cites W2970371739 @default.
• W3150874721 cites W2971076774 @default.
• W3150874721 cites W2997233328 @default.
• W3150874721 cites W3091123787 @default.
• W3150874721 cites W3104876213 @default.
• W3150874721 cites W3118608800 @default.
• W3150874721 cites W3129007965 @default.
• W3150874721 cites W3153924672 @default.
• W3150874721 hasPublicationYear "2021" @default.
• W3150874721 type Work @default.
• W3150874721 sameAs 3150874721 @default.
• W3150874721 citedByCount "0" @default.
• W3150874721 crossrefType "posted-content" @default.
• W3150874721 hasAuthorship W3150874721A5020279598 @default.
• W3150874721 hasAuthorship W3150874721A5091239620 @default.
• W3150874721 hasConcept C108583219 @default.
• W3150874721 hasConcept C113775141 @default.
• W3150874721 hasConcept C115961682 @default.
• W3150874721 hasConcept C119857082 @default.
• W3150874721 hasConcept C121332964 @default.
• W3150874721 hasConcept C153083717 @default.
• W3150874721 hasConcept C154945302 @default.
• W3150874721 hasConcept C163258240 @default.
• W3150874721 hasConcept C2776135515 @default.
• W3150874721 hasConcept C2780992000 @default.
• W3150874721 hasConcept C2988773926 @default.
• W3150874721 hasConcept C2989087649 @default.
• W3150874721 hasConcept C37736160 @default.
• W3150874721 hasConcept C39890363 @default.
• W3150874721 hasConcept C41008148 @default.
• W3150874721 hasConcept C62520636 @default.
• W3150874721 hasConcept C80444323 @default.
• W3150874721 hasConcept C81363708 @default.
• W3150874721 hasConceptScore W3150874721C108583219 @default.
• W3150874721 hasConceptScore W3150874721C113775141 @default.
• W3150874721 hasConceptScore W3150874721C115961682 @default.
• W3150874721 hasConceptScore W3150874721C119857082 @default.
• W3150874721 hasConceptScore W3150874721C121332964 @default.
• W3150874721 hasConceptScore W3150874721C153083717 @default.
• W3150874721 hasConceptScore W3150874721C154945302 @default.
• W3150874721 hasConceptScore W3150874721C163258240 @default.
• W3150874721 hasConceptScore W3150874721C2776135515 @default.
• W3150874721 hasConceptScore W3150874721C2780992000 @default.
• W3150874721 hasConceptScore W3150874721C2988773926 @default.
• W3150874721 hasConceptScore W3150874721C2989087649 @default.
• W3150874721 hasConceptScore W3150874721C37736160 @default.
• W3150874721 hasConceptScore W3150874721C39890363 @default.
• W3150874721 hasConceptScore W3150874721C41008148 @default.
• W3150874721 hasConceptScore W3150874721C62520636 @default.
• W3150874721 hasConceptScore W3150874721C80444323 @default.
• W3150874721 hasConceptScore W3150874721C81363708 @default.
• W3150874721 hasLocation W31508747211 @default.
• W3150874721 hasOpenAccess W3150874721 @default.
• W3150874721 hasPrimaryLocation W31508747211 @default.
• W3150874721 hasRelatedWork W2793676054 @default.
• W3150874721 hasRelatedWork W2794968447 @default.
• W3150874721 hasRelatedWork W2804184144 @default.

• next