Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955804572> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2955804572 abstract "After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an interpretable and factorized representation of latent variable by modifying their objective function or model architecture. To disentangle the latent variable, some models show lower quality of reconstructed images and others increase the model complexity which is hard to train. In this paper, we propose a simple disentangling method based on a traditional whitening process. The proposed method is applied to the latent variables of variational auto-encoder (VAE), although it can be applied to any generative models with latent variables. In experiment, we apply the proposed method to simple VAE models and experiment results confirm that our method finds more interpretable factors from the latent space while keeping the reconstruction error the same as the conventional VAE's error." @default.
- W2955804572 created "2019-07-12" @default.
- W2955804572 creator A5016861708 @default.
- W2955804572 creator A5079848178 @default.
- W2955804572 date "2018-11-08" @default.
- W2955804572 modified "2023-09-27" @default.
- W2955804572 title "Disentangling Latent Factors of Variational Auto-Encoder with Whitening" @default.
- W2955804572 cites W1834627138 @default.
- W2955804572 cites W2095439994 @default.
- W2955804572 cites W2099471712 @default.
- W2955804572 cites W2112796928 @default.
- W2955804572 cites W2155183960 @default.
- W2955804572 cites W2163922914 @default.
- W2955804572 cites W2166944917 @default.
- W2955804572 cites W2739748921 @default.
- W2955804572 cites W2753738274 @default.
- W2955804572 cites W2785961484 @default.
- W2955804572 cites W2951004968 @default.
- W2955804572 cites W2963104724 @default.
- W2955804572 cites W2963226019 @default.
- W2955804572 hasPublicationYear "2018" @default.
- W2955804572 type Work @default.
- W2955804572 sameAs 2955804572 @default.
- W2955804572 citedByCount "1" @default.
- W2955804572 countsByYear W29558045722019 @default.
- W2955804572 crossrefType "posted-content" @default.
- W2955804572 hasAuthorship W2955804572A5016861708 @default.
- W2955804572 hasAuthorship W2955804572A5079848178 @default.
- W2955804572 hasConcept C111472728 @default.
- W2955804572 hasConcept C111919701 @default.
- W2955804572 hasConcept C118505674 @default.
- W2955804572 hasConcept C119857082 @default.
- W2955804572 hasConcept C138885662 @default.
- W2955804572 hasConcept C153180895 @default.
- W2955804572 hasConcept C154945302 @default.
- W2955804572 hasConcept C167966045 @default.
- W2955804572 hasConcept C17744445 @default.
- W2955804572 hasConcept C199539241 @default.
- W2955804572 hasConcept C2776359362 @default.
- W2955804572 hasConcept C2780586882 @default.
- W2955804572 hasConcept C39890363 @default.
- W2955804572 hasConcept C41008148 @default.
- W2955804572 hasConcept C51167844 @default.
- W2955804572 hasConcept C65965080 @default.
- W2955804572 hasConcept C94625758 @default.
- W2955804572 hasConcept C98045186 @default.
- W2955804572 hasConceptScore W2955804572C111472728 @default.
- W2955804572 hasConceptScore W2955804572C111919701 @default.
- W2955804572 hasConceptScore W2955804572C118505674 @default.
- W2955804572 hasConceptScore W2955804572C119857082 @default.
- W2955804572 hasConceptScore W2955804572C138885662 @default.
- W2955804572 hasConceptScore W2955804572C153180895 @default.
- W2955804572 hasConceptScore W2955804572C154945302 @default.
- W2955804572 hasConceptScore W2955804572C167966045 @default.
- W2955804572 hasConceptScore W2955804572C17744445 @default.
- W2955804572 hasConceptScore W2955804572C199539241 @default.
- W2955804572 hasConceptScore W2955804572C2776359362 @default.
- W2955804572 hasConceptScore W2955804572C2780586882 @default.
- W2955804572 hasConceptScore W2955804572C39890363 @default.
- W2955804572 hasConceptScore W2955804572C41008148 @default.
- W2955804572 hasConceptScore W2955804572C51167844 @default.
- W2955804572 hasConceptScore W2955804572C65965080 @default.
- W2955804572 hasConceptScore W2955804572C94625758 @default.
- W2955804572 hasConceptScore W2955804572C98045186 @default.
- W2955804572 hasLocation W29558045721 @default.
- W2955804572 hasOpenAccess W2955804572 @default.
- W2955804572 hasPrimaryLocation W29558045721 @default.
- W2955804572 hasRelatedWork W2128791906 @default.
- W2955804572 hasRelatedWork W2170710952 @default.
- W2955804572 hasRelatedWork W2576084407 @default.
- W2955804572 hasRelatedWork W2766236296 @default.
- W2955804572 hasRelatedWork W2771620380 @default.
- W2955804572 hasRelatedWork W2786823319 @default.
- W2955804572 hasRelatedWork W2945924057 @default.
- W2955804572 hasRelatedWork W2979915069 @default.
- W2955804572 hasRelatedWork W2986440166 @default.
- W2955804572 hasRelatedWork W2989511902 @default.
- W2955804572 hasRelatedWork W2996397324 @default.
- W2955804572 hasRelatedWork W3006189318 @default.
- W2955804572 hasRelatedWork W3010693052 @default.
- W2955804572 hasRelatedWork W3025675478 @default.
- W2955804572 hasRelatedWork W3034107787 @default.
- W2955804572 hasRelatedWork W3126935830 @default.
- W2955804572 hasRelatedWork W3131488435 @default.
- W2955804572 hasRelatedWork W3171932471 @default.
- W2955804572 hasRelatedWork W3206452946 @default.
- W2955804572 hasRelatedWork W3209936399 @default.
- W2955804572 isParatext "false" @default.
- W2955804572 isRetracted "false" @default.
- W2955804572 magId "2955804572" @default.
- W2955804572 workType "article" @default.