FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891762668> ?p ?o ?g. }

• W2891762668 abstract "Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which can be important for datasets such as facial images. A GAN can transform a simple distribution to a latent-space data distribution and thus preserve the manifold structure, but optimizing a GAN involves solving a Min-Max optimization problem, which is difficult and not well understood so far. Therefore, we propose a GAN-like method to transform a simple distribution to a data distribution in the latent space by solving only a minimization problem. This minimization problem comes from training a discriminator between a simple distribution and a latent-space data distribution. Then, we can explicitly formulate an Optimal Transport (OT) problem that computes the desired mapping between the two distributions. This means that we can transform a distribution without solving the difficult Min-Max optimization problem. Experimental results on an eight-Gaussian dataset show that the proposed OT can handle multi-cluster distributions. Results on the MNIST and the CelebA datasets validate the effectiveness of the proposed method." @default.
• W2891762668 created "2018-09-27" @default.
• W2891762668 creator A5006865040 @default.
• W2891762668 creator A5034904892 @default.
• W2891762668 creator A5035967128 @default.
• W2891762668 creator A5046769911 @default.
• W2891762668 creator A5049677402 @default.
• W2891762668 creator A5076307452 @default.
• W2891762668 creator A5086990531 @default.
• W2891762668 date "2018-09-16" @default.
• W2891762668 modified "2023-10-18" @default.
• W2891762668 title "Latent Space Optimal Transport for Generative Models." @default.
• W2891762668 cites W1575501403 @default.
• W2891762668 cites W1834627138 @default.
• W2891762668 cites W1959608418 @default.
• W2891762668 cites W2036476394 @default.
• W2891762668 cites W2052643735 @default.
• W2891762668 cites W2075948878 @default.
• W2891762668 cites W2099471712 @default.
• W2891762668 cites W2112796928 @default.
• W2891762668 cites W2125389028 @default.
• W2891762668 cites W2132883347 @default.
• W2891762668 cites W2161086299 @default.
• W2891762668 cites W2173517407 @default.
• W2891762668 cites W2173520492 @default.
• W2891762668 cites W2555632090 @default.
• W2891762668 cites W2605195953 @default.
• W2891762668 cites W2607059968 @default.
• W2891762668 cites W2607170299 @default.
• W2891762668 cites W2611104282 @default.
• W2891762668 cites W2611147814 @default.
• W2891762668 cites W2738588019 @default.
• W2891762668 cites W2739748921 @default.
• W2891762668 cites W2775584822 @default.
• W2891762668 cites W2777654136 @default.
• W2891762668 cites W2803470640 @default.
• W2891762668 cites W2952673310 @default.
• W2891762668 cites W2962793481 @default.
• W2891762668 cites W2962879692 @default.
• W2891762668 cites W2963373786 @default.
• W2891762668 cites W2963746531 @default.
• W2891762668 cites W2963799213 @default.
• W2891762668 cites W2963836885 @default.
• W2891762668 cites W2963875852 @default.
• W2891762668 cites W2964121744 @default.
• W2891762668 cites W2964167449 @default.
• W2891762668 cites W2964252913 @default.
• W2891762668 hasPublicationYear "2018" @default.
• W2891762668 type Work @default.
• W2891762668 sameAs 2891762668 @default.
• W2891762668 citedByCount "2" @default.
• W2891762668 countsByYear W28917626682019 @default.
• W2891762668 countsByYear W28917626682020 @default.
• W2891762668 crossrefType "posted-content" @default.
• W2891762668 hasAuthorship W2891762668A5006865040 @default.
• W2891762668 hasAuthorship W2891762668A5034904892 @default.
• W2891762668 hasAuthorship W2891762668A5035967128 @default.
• W2891762668 hasAuthorship W2891762668A5046769911 @default.
• W2891762668 hasAuthorship W2891762668A5049677402 @default.
• W2891762668 hasAuthorship W2891762668A5076307452 @default.
• W2891762668 hasAuthorship W2891762668A5086990531 @default.
• W2891762668 hasConcept C107673813 @default.
• W2891762668 hasConcept C108583219 @default.
• W2891762668 hasConcept C110121322 @default.
• W2891762668 hasConcept C111472728 @default.
• W2891762668 hasConcept C111919701 @default.
• W2891762668 hasConcept C11413529 @default.
• W2891762668 hasConcept C121332964 @default.
• W2891762668 hasConcept C126255220 @default.
• W2891762668 hasConcept C127413603 @default.
• W2891762668 hasConcept C134306372 @default.
• W2891762668 hasConcept C138885662 @default.
• W2891762668 hasConcept C153180895 @default.
• W2891762668 hasConcept C154945302 @default.
• W2891762668 hasConcept C163716315 @default.
• W2891762668 hasConcept C177769412 @default.
• W2891762668 hasConcept C190502265 @default.
• W2891762668 hasConcept C2778572836 @default.
• W2891762668 hasConcept C2780586882 @default.
• W2891762668 hasConcept C28826006 @default.
• W2891762668 hasConcept C33923547 @default.
• W2891762668 hasConcept C41008148 @default.
• W2891762668 hasConcept C529865628 @default.
• W2891762668 hasConcept C62520636 @default.
• W2891762668 hasConcept C78519656 @default.
• W2891762668 hasConceptScore W2891762668C107673813 @default.
• W2891762668 hasConceptScore W2891762668C108583219 @default.
• W2891762668 hasConceptScore W2891762668C110121322 @default.
• W2891762668 hasConceptScore W2891762668C111472728 @default.
• W2891762668 hasConceptScore W2891762668C111919701 @default.
• W2891762668 hasConceptScore W2891762668C11413529 @default.
• W2891762668 hasConceptScore W2891762668C121332964 @default.
• W2891762668 hasConceptScore W2891762668C126255220 @default.
• W2891762668 hasConceptScore W2891762668C127413603 @default.
• W2891762668 hasConceptScore W2891762668C134306372 @default.
• W2891762668 hasConceptScore W2891762668C138885662 @default.
• W2891762668 hasConceptScore W2891762668C153180895 @default.
• W2891762668 hasConceptScore W2891762668C154945302 @default.
• W2891762668 hasConceptScore W2891762668C163716315 @default.
• W2891762668 hasConceptScore W2891762668C177769412 @default.

• next