Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287237172> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4287237172 abstract "Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN models on limited data. We theoretically show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data. Extensive experiments on several benchmark datasets demonstrate that the proposed regularization scheme 1) improves the generalization performance and stabilizes the learning dynamics of GAN models under limited training data, and 2) complements the recent data augmentation methods. These properties facilitate training GAN models to achieve state-of-the-art performance when only limited training data of the ImageNet benchmark is available." @default.
- W4287237172 created "2022-07-25" @default.
- W4287237172 creator A5015327348 @default.
- W4287237172 creator A5044127793 @default.
- W4287237172 creator A5052662458 @default.
- W4287237172 creator A5063179713 @default.
- W4287237172 creator A5090586839 @default.
- W4287237172 date "2021-04-07" @default.
- W4287237172 modified "2023-10-16" @default.
- W4287237172 title "Regularizing Generative Adversarial Networks under Limited Data" @default.
- W4287237172 hasPublicationYear "2021" @default.
- W4287237172 type Work @default.
- W4287237172 citedByCount "0" @default.
- W4287237172 crossrefType "posted-content" @default.
- W4287237172 hasAuthorship W4287237172A5015327348 @default.
- W4287237172 hasAuthorship W4287237172A5044127793 @default.
- W4287237172 hasAuthorship W4287237172A5052662458 @default.
- W4287237172 hasAuthorship W4287237172A5063179713 @default.
- W4287237172 hasAuthorship W4287237172A5090586839 @default.
- W4287237172 hasBestOaLocation W42872371721 @default.
- W4287237172 hasConcept C108583219 @default.
- W4287237172 hasConcept C119857082 @default.
- W4287237172 hasConcept C12267149 @default.
- W4287237172 hasConcept C13280743 @default.
- W4287237172 hasConcept C134306372 @default.
- W4287237172 hasConcept C138885662 @default.
- W4287237172 hasConcept C154945302 @default.
- W4287237172 hasConcept C177148314 @default.
- W4287237172 hasConcept C185798385 @default.
- W4287237172 hasConcept C205649164 @default.
- W4287237172 hasConcept C207390915 @default.
- W4287237172 hasConcept C2776135515 @default.
- W4287237172 hasConcept C2988773926 @default.
- W4287237172 hasConcept C33923547 @default.
- W4287237172 hasConcept C37736160 @default.
- W4287237172 hasConcept C39890363 @default.
- W4287237172 hasConcept C39891107 @default.
- W4287237172 hasConcept C41008148 @default.
- W4287237172 hasConcept C41895202 @default.
- W4287237172 hasConcept C51632099 @default.
- W4287237172 hasConceptScore W4287237172C108583219 @default.
- W4287237172 hasConceptScore W4287237172C119857082 @default.
- W4287237172 hasConceptScore W4287237172C12267149 @default.
- W4287237172 hasConceptScore W4287237172C13280743 @default.
- W4287237172 hasConceptScore W4287237172C134306372 @default.
- W4287237172 hasConceptScore W4287237172C138885662 @default.
- W4287237172 hasConceptScore W4287237172C154945302 @default.
- W4287237172 hasConceptScore W4287237172C177148314 @default.
- W4287237172 hasConceptScore W4287237172C185798385 @default.
- W4287237172 hasConceptScore W4287237172C205649164 @default.
- W4287237172 hasConceptScore W4287237172C207390915 @default.
- W4287237172 hasConceptScore W4287237172C2776135515 @default.
- W4287237172 hasConceptScore W4287237172C2988773926 @default.
- W4287237172 hasConceptScore W4287237172C33923547 @default.
- W4287237172 hasConceptScore W4287237172C37736160 @default.
- W4287237172 hasConceptScore W4287237172C39890363 @default.
- W4287237172 hasConceptScore W4287237172C39891107 @default.
- W4287237172 hasConceptScore W4287237172C41008148 @default.
- W4287237172 hasConceptScore W4287237172C41895202 @default.
- W4287237172 hasConceptScore W4287237172C51632099 @default.
- W4287237172 hasLocation W42872371721 @default.
- W4287237172 hasOpenAccess W4287237172 @default.
- W4287237172 hasPrimaryLocation W42872371721 @default.
- W4287237172 hasRelatedWork W10719664 @default.
- W4287237172 hasRelatedWork W12829028 @default.
- W4287237172 hasRelatedWork W13034104 @default.
- W4287237172 hasRelatedWork W14471487 @default.
- W4287237172 hasRelatedWork W14828854 @default.
- W4287237172 hasRelatedWork W14993799 @default.
- W4287237172 hasRelatedWork W482614 @default.
- W4287237172 hasRelatedWork W482721 @default.
- W4287237172 hasRelatedWork W728297 @default.
- W4287237172 hasRelatedWork W7724241 @default.
- W4287237172 isParatext "false" @default.
- W4287237172 isRetracted "false" @default.
- W4287237172 workType "article" @default.