Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308673310> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4308673310 endingPage "51" @default.
- W4308673310 startingPage "36" @default.
- W4308673310 abstract "We present a self-supervised method to disentangle factors of variation in high-dimensional data that does not rely on prior knowledge of the underlying variation profile (e.g., no assumptions on the number or distribution of the individual latent variables to be extracted). In this method which we call NashAE, high-dimensional feature disentanglement is accomplished in the low-dimensional latent space of a standard autoencoder (AE) by promoting the discrepancy between each encoding element and information of the element recovered from all other encoding elements. Disentanglement is promoted efficiently by framing this as a minmax game between the AE and an ensemble of regression networks which each provide an estimate of an element conditioned on an observation of all other elements. We quantitatively compare our approach with leading disentanglement methods using existing disentanglement metrics. Furthermore, we show that NashAE has increased reliability and increased capacity to capture salient data characteristics in the learned latent representation." @default.
- W4308673310 created "2022-11-14" @default.
- W4308673310 creator A5006587869 @default.
- W4308673310 creator A5069190300 @default.
- W4308673310 creator A5076990167 @default.
- W4308673310 creator A5090824296 @default.
- W4308673310 date "2022-01-01" @default.
- W4308673310 modified "2023-10-18" @default.
- W4308673310 title "NashAE: Disentangling Representations Through Adversarial Covariance Minimization" @default.
- W4308673310 cites W16016350 @default.
- W4308673310 cites W1834627138 @default.
- W4308673310 cites W2194775991 @default.
- W4308673310 cites W2405774341 @default.
- W4308673310 cites W2768346313 @default.
- W4308673310 cites W2890680318 @default.
- W4308673310 cites W2939569248 @default.
- W4308673310 cites W2945976633 @default.
- W4308673310 cites W3034665124 @default.
- W4308673310 doi "https://doi.org/10.1007/978-3-031-19812-0_3" @default.
- W4308673310 hasPublicationYear "2022" @default.
- W4308673310 type Work @default.
- W4308673310 citedByCount "0" @default.
- W4308673310 crossrefType "book-chapter" @default.
- W4308673310 hasAuthorship W4308673310A5006587869 @default.
- W4308673310 hasAuthorship W4308673310A5069190300 @default.
- W4308673310 hasAuthorship W4308673310A5076990167 @default.
- W4308673310 hasAuthorship W4308673310A5090824296 @default.
- W4308673310 hasBestOaLocation W43086733102 @default.
- W4308673310 hasConcept C101738243 @default.
- W4308673310 hasConcept C105795698 @default.
- W4308673310 hasConcept C119857082 @default.
- W4308673310 hasConcept C121332964 @default.
- W4308673310 hasConcept C124101348 @default.
- W4308673310 hasConcept C126255220 @default.
- W4308673310 hasConcept C149728462 @default.
- W4308673310 hasConcept C153180895 @default.
- W4308673310 hasConcept C154945302 @default.
- W4308673310 hasConcept C17744445 @default.
- W4308673310 hasConcept C178650346 @default.
- W4308673310 hasConcept C199539241 @default.
- W4308673310 hasConcept C2776359362 @default.
- W4308673310 hasConcept C2778334786 @default.
- W4308673310 hasConcept C2780719617 @default.
- W4308673310 hasConcept C33923547 @default.
- W4308673310 hasConcept C37736160 @default.
- W4308673310 hasConcept C41008148 @default.
- W4308673310 hasConcept C44870925 @default.
- W4308673310 hasConcept C50644808 @default.
- W4308673310 hasConcept C51167844 @default.
- W4308673310 hasConcept C83665646 @default.
- W4308673310 hasConcept C94625758 @default.
- W4308673310 hasConceptScore W4308673310C101738243 @default.
- W4308673310 hasConceptScore W4308673310C105795698 @default.
- W4308673310 hasConceptScore W4308673310C119857082 @default.
- W4308673310 hasConceptScore W4308673310C121332964 @default.
- W4308673310 hasConceptScore W4308673310C124101348 @default.
- W4308673310 hasConceptScore W4308673310C126255220 @default.
- W4308673310 hasConceptScore W4308673310C149728462 @default.
- W4308673310 hasConceptScore W4308673310C153180895 @default.
- W4308673310 hasConceptScore W4308673310C154945302 @default.
- W4308673310 hasConceptScore W4308673310C17744445 @default.
- W4308673310 hasConceptScore W4308673310C178650346 @default.
- W4308673310 hasConceptScore W4308673310C199539241 @default.
- W4308673310 hasConceptScore W4308673310C2776359362 @default.
- W4308673310 hasConceptScore W4308673310C2778334786 @default.
- W4308673310 hasConceptScore W4308673310C2780719617 @default.
- W4308673310 hasConceptScore W4308673310C33923547 @default.
- W4308673310 hasConceptScore W4308673310C37736160 @default.
- W4308673310 hasConceptScore W4308673310C41008148 @default.
- W4308673310 hasConceptScore W4308673310C44870925 @default.
- W4308673310 hasConceptScore W4308673310C50644808 @default.
- W4308673310 hasConceptScore W4308673310C51167844 @default.
- W4308673310 hasConceptScore W4308673310C83665646 @default.
- W4308673310 hasConceptScore W4308673310C94625758 @default.
- W4308673310 hasLocation W43086733101 @default.
- W4308673310 hasLocation W43086733102 @default.
- W4308673310 hasLocation W43086733103 @default.
- W4308673310 hasOpenAccess W4308673310 @default.
- W4308673310 hasPrimaryLocation W43086733101 @default.
- W4308673310 hasRelatedWork W2323792602 @default.
- W4308673310 hasRelatedWork W2772780115 @default.
- W4308673310 hasRelatedWork W2785535669 @default.
- W4308673310 hasRelatedWork W2899817933 @default.
- W4308673310 hasRelatedWork W2998168123 @default.
- W4308673310 hasRelatedWork W4220775285 @default.
- W4308673310 hasRelatedWork W4220810357 @default.
- W4308673310 hasRelatedWork W4287995534 @default.
- W4308673310 hasRelatedWork W4308673310 @default.
- W4308673310 hasRelatedWork W4312278779 @default.
- W4308673310 isParatext "false" @default.
- W4308673310 isRetracted "false" @default.
- W4308673310 workType "book-chapter" @default.