Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897959392> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2897959392 abstract "Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to explicitly label all the factors of interest in training images. To alleviate the annotation cost, we introduce a learning setting which we refer to as disentangling. Given a pool of unlabeled images, the goal is to learn a representation where a of target factors are disentangled from others. The only supervision comes from an auxiliary set containing images where the factors of interest are constant. In order to address this problem, we propose reference-based variational autoencoders, a novel deep generative model designed to exploit the weak-supervision provided by the reference set. By addressing tasks such as feature learning, conditional image generation or attribute transfer, we validate the ability of the proposed model to learn disentangled representations from this minimal form of supervision." @default.
- W2897959392 created "2018-10-26" @default.
- W2897959392 creator A5005841775 @default.
- W2897959392 creator A5005880103 @default.
- W2897959392 creator A5029618687 @default.
- W2897959392 creator A5040312210 @default.
- W2897959392 date "2019-05-06" @default.
- W2897959392 modified "2023-09-27" @default.
- W2897959392 title "Learning Disentangled Representations with Reference-Based Variational Autoencoders" @default.
- W2897959392 cites W1595126664 @default.
- W2897959392 cites W1691728462 @default.
- W2897959392 cites W1786904711 @default.
- W2897959392 cites W1959608418 @default.
- W2897959392 cites W1966026565 @default.
- W2897959392 cites W2099471712 @default.
- W2897959392 cites W2108501770 @default.
- W2897959392 cites W2112796928 @default.
- W2897959392 cites W2157285372 @default.
- W2897959392 cites W2163922914 @default.
- W2897959392 cites W2188956040 @default.
- W2897959392 cites W2423557781 @default.
- W2897959392 cites W2434741482 @default.
- W2897959392 cites W2559823555 @default.
- W2897959392 cites W2594374979 @default.
- W2897959392 cites W2615413256 @default.
- W2897959392 cites W2624918875 @default.
- W2897959392 cites W2745497104 @default.
- W2897959392 cites W2753738274 @default.
- W2897959392 cites W2785519580 @default.
- W2897959392 cites W2951326654 @default.
- W2897959392 cites W2952673310 @default.
- W2897959392 cites W2962760235 @default.
- W2897959392 cites W2962798930 @default.
- W2897959392 cites W2962818303 @default.
- W2897959392 cites W2962897886 @default.
- W2897959392 cites W2962975391 @default.
- W2897959392 cites W2963045453 @default.
- W2897959392 cites W2963125871 @default.
- W2897959392 cites W2963205805 @default.
- W2897959392 cites W2963264829 @default.
- W2897959392 cites W2963366547 @default.
- W2897959392 cites W2963567641 @default.
- W2897959392 cites W2963592272 @default.
- W2897959392 cites W2963618559 @default.
- W2897959392 cites W2964121744 @default.
- W2897959392 cites W2964127395 @default.
- W2897959392 cites W2964168187 @default.
- W2897959392 hasPublicationYear "2019" @default.
- W2897959392 type Work @default.
- W2897959392 sameAs 2897959392 @default.
- W2897959392 citedByCount "10" @default.
- W2897959392 countsByYear W28979593922019 @default.
- W2897959392 countsByYear W28979593922020 @default.
- W2897959392 crossrefType "proceedings-article" @default.
- W2897959392 hasAuthorship W2897959392A5005841775 @default.
- W2897959392 hasAuthorship W2897959392A5005880103 @default.
- W2897959392 hasAuthorship W2897959392A5029618687 @default.
- W2897959392 hasAuthorship W2897959392A5040312210 @default.
- W2897959392 hasBestOaLocation W28979593921 @default.
- W2897959392 hasConcept C119857082 @default.
- W2897959392 hasConcept C154945302 @default.
- W2897959392 hasConcept C204321447 @default.
- W2897959392 hasConcept C41008148 @default.
- W2897959392 hasConcept C80444323 @default.
- W2897959392 hasConceptScore W2897959392C119857082 @default.
- W2897959392 hasConceptScore W2897959392C154945302 @default.
- W2897959392 hasConceptScore W2897959392C204321447 @default.
- W2897959392 hasConceptScore W2897959392C41008148 @default.
- W2897959392 hasConceptScore W2897959392C80444323 @default.
- W2897959392 hasLocation W28979593921 @default.
- W2897959392 hasLocation W28979593922 @default.
- W2897959392 hasLocation W28979593923 @default.
- W2897959392 hasLocation W28979593924 @default.
- W2897959392 hasOpenAccess W2897959392 @default.
- W2897959392 hasPrimaryLocation W28979593921 @default.
- W2897959392 hasRelatedWork W2611614995 @default.
- W2897959392 hasRelatedWork W2961085424 @default.
- W2897959392 hasRelatedWork W3046775127 @default.
- W2897959392 hasRelatedWork W3107474891 @default.
- W2897959392 hasRelatedWork W4205958290 @default.
- W2897959392 hasRelatedWork W4285260836 @default.
- W2897959392 hasRelatedWork W4286629047 @default.
- W2897959392 hasRelatedWork W4306321456 @default.
- W2897959392 hasRelatedWork W4306674287 @default.
- W2897959392 hasRelatedWork W4224009465 @default.
- W2897959392 isParatext "false" @default.
- W2897959392 isRetracted "false" @default.
- W2897959392 magId "2897959392" @default.
- W2897959392 workType "article" @default.