Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912961385> ?p ?o ?g. }
- W2912961385 abstract "Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Despite their computational efficiency, the density estimation performance of flow-based generative models significantly falls behind those of state-of-the-art autoregressive models. In this work, we introduce masked convolutional generative flow (MaCow), a simple yet effective architecture of generative flow using masked convolution. By restricting the local connectivity in a small kernel, MaCow enjoys the properties of fast and stable training, and efficient sampling, while achieving significant improvements over Glow for density estimation on standard image benchmarks, considerably narrowing the gap to autoregressive models." @default.
- W2912961385 created "2019-02-21" @default.
- W2912961385 creator A5013030532 @default.
- W2912961385 creator A5015250671 @default.
- W2912961385 creator A5060225743 @default.
- W2912961385 creator A5078672329 @default.
- W2912961385 date "2019-02-12" @default.
- W2912961385 modified "2023-09-27" @default.
- W2912961385 title "MaCow: Masked Convolutional Generative Flow" @default.
- W2912961385 cites W1522301498 @default.
- W2912961385 cites W1583912456 @default.
- W2912961385 cites W1834627138 @default.
- W2912961385 cites W1836465849 @default.
- W2912961385 cites W1866230956 @default.
- W2912961385 cites W1959608418 @default.
- W2912961385 cites W2135181320 @default.
- W2912961385 cites W2140574335 @default.
- W2912961385 cites W2173520492 @default.
- W2912961385 cites W2176412452 @default.
- W2912961385 cites W2210838531 @default.
- W2912961385 cites W2267126114 @default.
- W2912961385 cites W2409550820 @default.
- W2912961385 cites W2587284713 @default.
- W2912961385 cites W2778792233 @default.
- W2912961385 cites W2893749619 @default.
- W2912961385 cites W2898847420 @default.
- W2912961385 cites W2899771611 @default.
- W2912961385 cites W2902630600 @default.
- W2912961385 cites W2911827218 @default.
- W2912961385 cites W2912618358 @default.
- W2912961385 cites W2949382160 @default.
- W2912961385 cites W2962750131 @default.
- W2912961385 cites W2962760235 @default.
- W2912961385 cites W2962844293 @default.
- W2912961385 cites W2963047245 @default.
- W2912961385 cites W2963139417 @default.
- W2912961385 cites W2963636093 @default.
- W2912961385 cites W2963857374 @default.
- W2912961385 cites W299440670 @default.
- W2912961385 cites W3118608800 @default.
- W2912961385 cites W967544008 @default.
- W2912961385 hasPublicationYear "2019" @default.
- W2912961385 type Work @default.
- W2912961385 sameAs 2912961385 @default.
- W2912961385 citedByCount "4" @default.
- W2912961385 countsByYear W29129613852019 @default.
- W2912961385 countsByYear W29129613852021 @default.
- W2912961385 crossrefType "posted-content" @default.
- W2912961385 hasAuthorship W2912961385A5013030532 @default.
- W2912961385 hasAuthorship W2912961385A5015250671 @default.
- W2912961385 hasAuthorship W2912961385A5060225743 @default.
- W2912961385 hasAuthorship W2912961385A5078672329 @default.
- W2912961385 hasConcept C105795698 @default.
- W2912961385 hasConcept C106131492 @default.
- W2912961385 hasConcept C11413529 @default.
- W2912961385 hasConcept C114614502 @default.
- W2912961385 hasConcept C119857082 @default.
- W2912961385 hasConcept C140779682 @default.
- W2912961385 hasConcept C149782125 @default.
- W2912961385 hasConcept C154945302 @default.
- W2912961385 hasConcept C159877910 @default.
- W2912961385 hasConcept C167966045 @default.
- W2912961385 hasConcept C185429906 @default.
- W2912961385 hasConcept C189508267 @default.
- W2912961385 hasConcept C2524010 @default.
- W2912961385 hasConcept C2776214188 @default.
- W2912961385 hasConcept C31972630 @default.
- W2912961385 hasConcept C33923547 @default.
- W2912961385 hasConcept C38349280 @default.
- W2912961385 hasConcept C39890363 @default.
- W2912961385 hasConcept C41008148 @default.
- W2912961385 hasConcept C45347329 @default.
- W2912961385 hasConcept C45374587 @default.
- W2912961385 hasConcept C50644808 @default.
- W2912961385 hasConcept C51167844 @default.
- W2912961385 hasConcept C71134354 @default.
- W2912961385 hasConcept C74193536 @default.
- W2912961385 hasConceptScore W2912961385C105795698 @default.
- W2912961385 hasConceptScore W2912961385C106131492 @default.
- W2912961385 hasConceptScore W2912961385C11413529 @default.
- W2912961385 hasConceptScore W2912961385C114614502 @default.
- W2912961385 hasConceptScore W2912961385C119857082 @default.
- W2912961385 hasConceptScore W2912961385C140779682 @default.
- W2912961385 hasConceptScore W2912961385C149782125 @default.
- W2912961385 hasConceptScore W2912961385C154945302 @default.
- W2912961385 hasConceptScore W2912961385C159877910 @default.
- W2912961385 hasConceptScore W2912961385C167966045 @default.
- W2912961385 hasConceptScore W2912961385C185429906 @default.
- W2912961385 hasConceptScore W2912961385C189508267 @default.
- W2912961385 hasConceptScore W2912961385C2524010 @default.
- W2912961385 hasConceptScore W2912961385C2776214188 @default.
- W2912961385 hasConceptScore W2912961385C31972630 @default.
- W2912961385 hasConceptScore W2912961385C33923547 @default.
- W2912961385 hasConceptScore W2912961385C38349280 @default.
- W2912961385 hasConceptScore W2912961385C39890363 @default.
- W2912961385 hasConceptScore W2912961385C41008148 @default.
- W2912961385 hasConceptScore W2912961385C45347329 @default.
- W2912961385 hasConceptScore W2912961385C45374587 @default.
- W2912961385 hasConceptScore W2912961385C50644808 @default.
- W2912961385 hasConceptScore W2912961385C51167844 @default.