FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090794770> ?p ?o ?g. }

• W3090794770 abstract "While variational autoencoders have been successful in a variety of tasks, the use of conventional Gaussian or Gaussian mixture priors are limited in their ability to encode underlying structure of data in the latent representation. In this work, we introduce an Encoded Prior Sliced Wasserstein AutoEncoder (EPSWAE) wherein an additional prior-encoder network facilitates learns an embedding of the data manifold which preserves topological and geometric properties of the data, thus improving the structure of latent space. The autoencoder and prior-encoder networks are iteratively trained using the Sliced Wasserstein (SW) distance, which efficiently measures the distance between two textit{arbitrary} sampleable distributions without being constrained to a specific form as in the KL divergence, and without requiring expensive adversarial training. To improve the representation, we use (1) a structural consistency term in the loss that encourages isometry between feature space and latent space and (2) a nonlinear variant of the SW distance which averages over random nonlinear shearing. The effectiveness of the learned manifold encoding is best explored by traversing the latent space through interpolations along textit{geodesics} which generate samples that lie on the manifold and hence are advantageous compared to standard Euclidean interpolation. To this end, we introduce a graph-based algorithm for interpolating along network-geodesics in latent space by maximizing the density of samples along the path while minimizing total energy. We use the 3D-spiral data to show that the prior does indeed encode the geometry underlying the data and to demonstrate the advantages of the network-algorithm for interpolation. Additionally, we apply our framework to MNIST, and CelebA datasets, and show that outlier generations, latent representations, and geodesic interpolations are comparable to the state of the art." @default.
• W3090794770 created "2020-10-08" @default.
• W3090794770 creator A5002601106 @default.
• W3090794770 creator A5081815930 @default.
• W3090794770 date "2021-05-04" @default.
• W3090794770 modified "2023-09-27" @default.
• W3090794770 title "Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations" @default.
• W3090794770 cites W1585160083 @default.
• W3090794770 cites W1959608418 @default.
• W3090794770 cites W2001141328 @default.
• W3090794770 cites W2019106840 @default.
• W3090794770 cites W2035553724 @default.
• W3090794770 cites W2077360418 @default.
• W3090794770 cites W2169528473 @default.
• W3090794770 cites W2170237252 @default.
• W3090794770 cites W2288498609 @default.
• W3090794770 cites W2528578439 @default.
• W3090794770 cites W2554952599 @default.
• W3090794770 cites W2556467266 @default.
• W3090794770 cites W2592725663 @default.
• W3090794770 cites W2604977777 @default.
• W3090794770 cites W2753738274 @default.
• W3090794770 cites W2883961755 @default.
• W3090794770 cites W2949649223 @default.
• W3090794770 cites W2952584433 @default.
• W3090794770 cites W2962738009 @default.
• W3090794770 cites W2962879692 @default.
• W3090794770 cites W2962911072 @default.
• W3090794770 cites W2962964479 @default.
• W3090794770 cites W2963006832 @default.
• W3090794770 cites W2963090522 @default.
• W3090794770 cites W2963253162 @default.
• W3090794770 cites W2963275229 @default.
• W3090794770 cites W2963364041 @default.
• W3090794770 cites W2963693826 @default.
• W3090794770 cites W2963746531 @default.
• W3090794770 cites W2964011399 @default.
• W3090794770 cites W2964121744 @default.
• W3090794770 cites W2964231450 @default.
• W3090794770 cites W2970112944 @default.
• W3090794770 cites W2979557588 @default.
• W3090794770 cites W2980096013 @default.
• W3090794770 cites W3002254693 @default.
• W3090794770 cites W3005737261 @default.
• W3090794770 cites W3006034899 @default.
• W3090794770 cites W3009854800 @default.
• W3090794770 cites W3034224401 @default.
• W3090794770 cites W3034357933 @default.
• W3090794770 cites W3043129282 @default.
• W3090794770 cites W786520459 @default.
• W3090794770 cites W82869218 @default.
• W3090794770 hasPublicationYear "2021" @default.
• W3090794770 type Work @default.
• W3090794770 sameAs 3090794770 @default.
• W3090794770 citedByCount "0" @default.
• W3090794770 crossrefType "journal-article" @default.
• W3090794770 hasAuthorship W3090794770A5002601106 @default.
• W3090794770 hasAuthorship W3090794770A5081815930 @default.
• W3090794770 hasConcept C101738243 @default.
• W3090794770 hasConcept C11413529 @default.
• W3090794770 hasConcept C114614502 @default.
• W3090794770 hasConcept C127413603 @default.
• W3090794770 hasConcept C153180895 @default.
• W3090794770 hasConcept C154945302 @default.
• W3090794770 hasConcept C165818556 @default.
• W3090794770 hasConcept C184720557 @default.
• W3090794770 hasConcept C2524010 @default.
• W3090794770 hasConcept C2777634741 @default.
• W3090794770 hasConcept C28826006 @default.
• W3090794770 hasConcept C33923547 @default.
• W3090794770 hasConcept C41008148 @default.
• W3090794770 hasConcept C50644808 @default.
• W3090794770 hasConcept C529865628 @default.
• W3090794770 hasConcept C78519656 @default.
• W3090794770 hasConceptScore W3090794770C101738243 @default.
• W3090794770 hasConceptScore W3090794770C11413529 @default.
• W3090794770 hasConceptScore W3090794770C114614502 @default.
• W3090794770 hasConceptScore W3090794770C127413603 @default.
• W3090794770 hasConceptScore W3090794770C153180895 @default.
• W3090794770 hasConceptScore W3090794770C154945302 @default.
• W3090794770 hasConceptScore W3090794770C165818556 @default.
• W3090794770 hasConceptScore W3090794770C184720557 @default.
• W3090794770 hasConceptScore W3090794770C2524010 @default.
• W3090794770 hasConceptScore W3090794770C2777634741 @default.
• W3090794770 hasConceptScore W3090794770C28826006 @default.
• W3090794770 hasConceptScore W3090794770C33923547 @default.
• W3090794770 hasConceptScore W3090794770C41008148 @default.
• W3090794770 hasConceptScore W3090794770C50644808 @default.
• W3090794770 hasConceptScore W3090794770C529865628 @default.
• W3090794770 hasConceptScore W3090794770C78519656 @default.
• W3090794770 hasLocation W30907947701 @default.
• W3090794770 hasOpenAccess W3090794770 @default.
• W3090794770 hasPrimaryLocation W30907947701 @default.
• W3090794770 hasRelatedWork W1923358317 @default.
• W3090794770 hasRelatedWork W2724105803 @default.
• W3090794770 hasRelatedWork W2750790669 @default.
• W3090794770 hasRelatedWork W2770865047 @default.
• W3090794770 hasRelatedWork W2775786317 @default.
• W3090794770 hasRelatedWork W2789646393 @default.
• W3090794770 hasRelatedWork W2809744928 @default.

• next