Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894573160> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2894573160 endingPage "104" @default.
- W2894573160 startingPage "90" @default.
- W2894573160 abstract "The classic Generative Adversarial Net and its variants can be roughly categorized into two large families: the unregularized versus regularized GANs. By relaxing the non-parametric assumption on the discriminator in the classic GAN, the regularized GANs have better generalization ability to produce new samples drawn from the real distribution. It is well known that the real data like natural images are not uniformly distributed over the whole data space. Instead, they are often restricted to a low-dimensional manifold of the ambient space. Such a manifold assumption suggests the distance over the manifold should be a better measure to characterize the distinct between real and fake samples. Thus, we define a pullback operator to map samples back to their data manifold, and a manifold margin is defined as the distance between the pullback representations to distinguish between real and fake samples and learn the optimal generators. We justify the effectiveness of the proposed model both theoretically and empirically." @default.
- W2894573160 created "2018-10-12" @default.
- W2894573160 creator A5026424547 @default.
- W2894573160 creator A5082230753 @default.
- W2894573160 date "2018-01-01" @default.
- W2894573160 modified "2023-09-26" @default.
- W2894573160 title "Generalized Loss-Sensitive Adversarial Learning with Manifold Margins" @default.
- W2894573160 cites W2025276985 @default.
- W2894573160 cites W2028017042 @default.
- W2894573160 cites W2117539524 @default.
- W2894573160 cites W2147062276 @default.
- W2894573160 cites W2209882149 @default.
- W2894573160 cites W2963584589 @default.
- W2894573160 doi "https://doi.org/10.1007/978-3-030-01228-1_6" @default.
- W2894573160 hasPublicationYear "2018" @default.
- W2894573160 type Work @default.
- W2894573160 sameAs 2894573160 @default.
- W2894573160 citedByCount "25" @default.
- W2894573160 countsByYear W28945731602018 @default.
- W2894573160 countsByYear W28945731602019 @default.
- W2894573160 countsByYear W28945731602020 @default.
- W2894573160 countsByYear W28945731602021 @default.
- W2894573160 countsByYear W28945731602022 @default.
- W2894573160 countsByYear W28945731602023 @default.
- W2894573160 crossrefType "book-chapter" @default.
- W2894573160 hasAuthorship W2894573160A5026424547 @default.
- W2894573160 hasAuthorship W2894573160A5082230753 @default.
- W2894573160 hasConcept C11413529 @default.
- W2894573160 hasConcept C114614502 @default.
- W2894573160 hasConcept C119857082 @default.
- W2894573160 hasConcept C124101348 @default.
- W2894573160 hasConcept C127413603 @default.
- W2894573160 hasConcept C134306372 @default.
- W2894573160 hasConcept C151876577 @default.
- W2894573160 hasConcept C153120616 @default.
- W2894573160 hasConcept C154945302 @default.
- W2894573160 hasConcept C177148314 @default.
- W2894573160 hasConcept C184720557 @default.
- W2894573160 hasConcept C202444582 @default.
- W2894573160 hasConcept C2777680557 @default.
- W2894573160 hasConcept C2780009758 @default.
- W2894573160 hasConcept C33923547 @default.
- W2894573160 hasConcept C41008148 @default.
- W2894573160 hasConcept C529865628 @default.
- W2894573160 hasConcept C70518039 @default.
- W2894573160 hasConcept C774472 @default.
- W2894573160 hasConcept C78519656 @default.
- W2894573160 hasConceptScore W2894573160C11413529 @default.
- W2894573160 hasConceptScore W2894573160C114614502 @default.
- W2894573160 hasConceptScore W2894573160C119857082 @default.
- W2894573160 hasConceptScore W2894573160C124101348 @default.
- W2894573160 hasConceptScore W2894573160C127413603 @default.
- W2894573160 hasConceptScore W2894573160C134306372 @default.
- W2894573160 hasConceptScore W2894573160C151876577 @default.
- W2894573160 hasConceptScore W2894573160C153120616 @default.
- W2894573160 hasConceptScore W2894573160C154945302 @default.
- W2894573160 hasConceptScore W2894573160C177148314 @default.
- W2894573160 hasConceptScore W2894573160C184720557 @default.
- W2894573160 hasConceptScore W2894573160C202444582 @default.
- W2894573160 hasConceptScore W2894573160C2777680557 @default.
- W2894573160 hasConceptScore W2894573160C2780009758 @default.
- W2894573160 hasConceptScore W2894573160C33923547 @default.
- W2894573160 hasConceptScore W2894573160C41008148 @default.
- W2894573160 hasConceptScore W2894573160C529865628 @default.
- W2894573160 hasConceptScore W2894573160C70518039 @default.
- W2894573160 hasConceptScore W2894573160C774472 @default.
- W2894573160 hasConceptScore W2894573160C78519656 @default.
- W2894573160 hasLocation W28945731601 @default.
- W2894573160 hasOpenAccess W2894573160 @default.
- W2894573160 hasPrimaryLocation W28945731601 @default.
- W2894573160 hasRelatedWork W117517268 @default.
- W2894573160 hasRelatedWork W2375518579 @default.
- W2894573160 hasRelatedWork W2387045723 @default.
- W2894573160 hasRelatedWork W2397338926 @default.
- W2894573160 hasRelatedWork W2573981081 @default.
- W2894573160 hasRelatedWork W2604211872 @default.
- W2894573160 hasRelatedWork W2950509861 @default.
- W2894573160 hasRelatedWork W3109610583 @default.
- W2894573160 hasRelatedWork W65619410 @default.
- W2894573160 hasRelatedWork W1773365694 @default.
- W2894573160 isParatext "false" @default.
- W2894573160 isRetracted "false" @default.
- W2894573160 magId "2894573160" @default.
- W2894573160 workType "book-chapter" @default.