FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990706204> ?p ?o ?g. }

• W2990706204 abstract "Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes. In this work, we improve CS-GAN with natural gradient-based latent optimisation and show that it improves adversarial dynamics by enhancing interactions between the discriminator and the generator. Our experiments demonstrate that latent optimisation can significantly improve GAN training, obtaining state-of-the-art performance for the ImageNet ($128 times 128$) dataset. Our model achieves an Inception Score (IS) of $148$ and an Frechet Inception Distance (FID) of $3.4$, an improvement of $17%$ and $32%$ in IS and FID respectively, compared with the baseline BigGAN-deep model with the same architecture and number of parameters." @default.
• W2990706204 created "2019-12-05" @default.
• W2990706204 creator A5004625775 @default.
• W2990706204 creator A5011169641 @default.
• W2990706204 creator A5066294254 @default.
• W2990706204 creator A5070702602 @default.
• W2990706204 creator A5077819827 @default.
• W2990706204 date "2019-09-25" @default.
• W2990706204 modified "2023-10-01" @default.
• W2990706204 title "LOGAN: Latent Optimisation for Generative Adversarial Networks" @default.
• W2990706204 cites W1970789124 @default.
• W2990706204 cites W2006903949 @default.
• W2990706204 cites W2065134213 @default.
• W2990706204 cites W2082261506 @default.
• W2990706204 cites W2094364653 @default.
• W2990706204 cites W2099471712 @default.
• W2990706204 cites W2108598243 @default.
• W2990706204 cites W2164452299 @default.
• W2990706204 cites W2167433878 @default.
• W2990706204 cites W2173520492 @default.
• W2990706204 cites W2194775991 @default.
• W2990706204 cites W2296616510 @default.
• W2990706204 cites W2520707650 @default.
• W2990706204 cites W2554314924 @default.
• W2990706204 cites W2619503996 @default.
• W2990706204 cites W2792263949 @default.
• W2990706204 cites W2804078698 @default.
• W2990706204 cites W2885487913 @default.
• W2990706204 cites W2893749619 @default.
• W2990706204 cites W2914221386 @default.
• W2990706204 cites W2922772346 @default.
• W2990706204 cites W2944678322 @default.
• W2990706204 cites W2945125725 @default.
• W2990706204 cites W2950299304 @default.
• W2990706204 cites W2952745707 @default.
• W2990706204 cites W2952936466 @default.
• W2990706204 cites W2960404386 @default.
• W2990706204 cites W2962754210 @default.
• W2990706204 cites W2962770929 @default.
• W2990706204 cites W2962793481 @default.
• W2990706204 cites W2962979365 @default.
• W2990706204 cites W2963265008 @default.
• W2990706204 cites W2963373786 @default.
• W2990706204 cites W2963476931 @default.
• W2990706204 cites W2963504252 @default.
• W2990706204 cites W2963800509 @default.
• W2990706204 cites W2963836885 @default.
• W2990706204 cites W2963981733 @default.
• W2990706204 cites W2964309400 @default.
• W2990706204 cites W2970241862 @default.
• W2990706204 cites W2970938715 @default.
• W2990706204 cites W2971074500 @default.
• W2990706204 cites W2971337561 @default.
• W2990706204 cites W2976617189 @default.
• W2990706204 cites W2979776030 @default.
• W2990706204 cites W3037695135 @default.
• W2990706204 cites W3086499488 @default.
• W2990706204 cites W3189092450 @default.
• W2990706204 hasPublicationYear "2019" @default.
• W2990706204 type Work @default.
• W2990706204 sameAs 2990706204 @default.
• W2990706204 citedByCount "32" @default.
• W2990706204 countsByYear W29907062042020 @default.
• W2990706204 countsByYear W29907062042021 @default.
• W2990706204 crossrefType "posted-content" @default.
• W2990706204 hasAuthorship W2990706204A5004625775 @default.
• W2990706204 hasAuthorship W2990706204A5011169641 @default.
• W2990706204 hasAuthorship W2990706204A5066294254 @default.
• W2990706204 hasAuthorship W2990706204A5070702602 @default.
• W2990706204 hasAuthorship W2990706204A5077819827 @default.
• W2990706204 hasConcept C108583219 @default.
• W2990706204 hasConcept C119857082 @default.
• W2990706204 hasConcept C121332964 @default.
• W2990706204 hasConcept C12725497 @default.
• W2990706204 hasConcept C154945302 @default.
• W2990706204 hasConcept C163258240 @default.
• W2990706204 hasConcept C17744445 @default.
• W2990706204 hasConcept C199539241 @default.
• W2990706204 hasConcept C2779803651 @default.
• W2990706204 hasConcept C2780992000 @default.
• W2990706204 hasConcept C2988773926 @default.
• W2990706204 hasConcept C37736160 @default.
• W2990706204 hasConcept C39890363 @default.
• W2990706204 hasConcept C41008148 @default.
• W2990706204 hasConcept C51167844 @default.
• W2990706204 hasConcept C62520636 @default.
• W2990706204 hasConcept C76155785 @default.
• W2990706204 hasConcept C94915269 @default.
• W2990706204 hasConceptScore W2990706204C108583219 @default.
• W2990706204 hasConceptScore W2990706204C119857082 @default.
• W2990706204 hasConceptScore W2990706204C121332964 @default.
• W2990706204 hasConceptScore W2990706204C12725497 @default.
• W2990706204 hasConceptScore W2990706204C154945302 @default.
• W2990706204 hasConceptScore W2990706204C163258240 @default.
• W2990706204 hasConceptScore W2990706204C17744445 @default.
• W2990706204 hasConceptScore W2990706204C199539241 @default.
• W2990706204 hasConceptScore W2990706204C2779803651 @default.
• W2990706204 hasConceptScore W2990706204C2780992000 @default.
• W2990706204 hasConceptScore W2990706204C2988773926 @default.
• W2990706204 hasConceptScore W2990706204C37736160 @default.

• next