Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210362717> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3210362717 endingPage "334" @default.
- W3210362717 startingPage "296" @default.
- W3210362717 abstract "Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are too sparse for reconstruction, whereas, in autoencoders the representations are dense but have limited indistinguishable class-specific features, making them less suitable for classification. In this work, we propose a discriminative modeling framework that employs manipulated supervised latent representations to reconstruct and generate new samples belonging to a given class. Unlike generative modeling approaches such as GANs and VAEs that aim to model the data manifold distribution, Representation based Generations (ReGene) directly represent the given data manifold in the classification space. Such supervised representations, under certain constraints, allow for reconstructions and controlled generations using an appropriate decoder without enforcing any prior distribution. Theoretically, given a class, we show that these representations when smartly manipulated using convex combinations retain the same class label. Furthermore, they also lead to the novel generation of visually realistic images. Extensive experiments on datasets of varying resolutions demonstrate that ReGene has higher classification accuracy than existing conditional generative models while being competitive in terms of FID." @default.
- W3210362717 created "2021-11-08" @default.
- W3210362717 creator A5001103949 @default.
- W3210362717 creator A5001375976 @default.
- W3210362717 creator A5041667369 @default.
- W3210362717 creator A5051935928 @default.
- W3210362717 creator A5064873292 @default.
- W3210362717 creator A5069021169 @default.
- W3210362717 date "2022-01-01" @default.
- W3210362717 modified "2023-10-06" @default.
- W3210362717 title "Classify and generate: Using classification latent space representations for image generations" @default.
- W3210362717 cites W2133665775 @default.
- W3210362717 cites W2618530766 @default.
- W3210362717 cites W2801026247 @default.
- W3210362717 cites W2884805522 @default.
- W3210362717 cites W3080275181 @default.
- W3210362717 doi "https://doi.org/10.1016/j.neucom.2021.10.090" @default.
- W3210362717 hasPublicationYear "2022" @default.
- W3210362717 type Work @default.
- W3210362717 sameAs 3210362717 @default.
- W3210362717 citedByCount "0" @default.
- W3210362717 crossrefType "journal-article" @default.
- W3210362717 hasAuthorship W3210362717A5001103949 @default.
- W3210362717 hasAuthorship W3210362717A5001375976 @default.
- W3210362717 hasAuthorship W3210362717A5041667369 @default.
- W3210362717 hasAuthorship W3210362717A5051935928 @default.
- W3210362717 hasAuthorship W3210362717A5064873292 @default.
- W3210362717 hasAuthorship W3210362717A5069021169 @default.
- W3210362717 hasBestOaLocation W32103627172 @default.
- W3210362717 hasConcept C107673813 @default.
- W3210362717 hasConcept C111919701 @default.
- W3210362717 hasConcept C119857082 @default.
- W3210362717 hasConcept C127413603 @default.
- W3210362717 hasConcept C153180895 @default.
- W3210362717 hasConcept C154945302 @default.
- W3210362717 hasConcept C167966045 @default.
- W3210362717 hasConcept C17744445 @default.
- W3210362717 hasConcept C177769412 @default.
- W3210362717 hasConcept C199539241 @default.
- W3210362717 hasConcept C2776359362 @default.
- W3210362717 hasConcept C2777212361 @default.
- W3210362717 hasConcept C2778572836 @default.
- W3210362717 hasConcept C39890363 @default.
- W3210362717 hasConcept C41008148 @default.
- W3210362717 hasConcept C529865628 @default.
- W3210362717 hasConcept C78519656 @default.
- W3210362717 hasConcept C94625758 @default.
- W3210362717 hasConcept C97931131 @default.
- W3210362717 hasConceptScore W3210362717C107673813 @default.
- W3210362717 hasConceptScore W3210362717C111919701 @default.
- W3210362717 hasConceptScore W3210362717C119857082 @default.
- W3210362717 hasConceptScore W3210362717C127413603 @default.
- W3210362717 hasConceptScore W3210362717C153180895 @default.
- W3210362717 hasConceptScore W3210362717C154945302 @default.
- W3210362717 hasConceptScore W3210362717C167966045 @default.
- W3210362717 hasConceptScore W3210362717C17744445 @default.
- W3210362717 hasConceptScore W3210362717C177769412 @default.
- W3210362717 hasConceptScore W3210362717C199539241 @default.
- W3210362717 hasConceptScore W3210362717C2776359362 @default.
- W3210362717 hasConceptScore W3210362717C2777212361 @default.
- W3210362717 hasConceptScore W3210362717C2778572836 @default.
- W3210362717 hasConceptScore W3210362717C39890363 @default.
- W3210362717 hasConceptScore W3210362717C41008148 @default.
- W3210362717 hasConceptScore W3210362717C529865628 @default.
- W3210362717 hasConceptScore W3210362717C78519656 @default.
- W3210362717 hasConceptScore W3210362717C94625758 @default.
- W3210362717 hasConceptScore W3210362717C97931131 @default.
- W3210362717 hasFunder F4320334744 @default.
- W3210362717 hasLocation W32103627171 @default.
- W3210362717 hasLocation W32103627172 @default.
- W3210362717 hasLocation W32103627173 @default.
- W3210362717 hasOpenAccess W3210362717 @default.
- W3210362717 hasPrimaryLocation W32103627171 @default.
- W3210362717 hasRelatedWork W156476889 @default.
- W3210362717 hasRelatedWork W1576360539 @default.
- W3210362717 hasRelatedWork W2024160000 @default.
- W3210362717 hasRelatedWork W2093104230 @default.
- W3210362717 hasRelatedWork W2729514902 @default.
- W3210362717 hasRelatedWork W2770426046 @default.
- W3210362717 hasRelatedWork W2773500201 @default.
- W3210362717 hasRelatedWork W3014948380 @default.
- W3210362717 hasRelatedWork W3205589360 @default.
- W3210362717 hasRelatedWork W4286907481 @default.
- W3210362717 hasVolume "471" @default.
- W3210362717 isParatext "false" @default.
- W3210362717 isRetracted "false" @default.
- W3210362717 magId "3210362717" @default.
- W3210362717 workType "article" @default.