Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913735045> ?p ?o ?g. }
- W2913735045 abstract "Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not necessarily faithful reproduction of the inputs. The main reason is to enforce the learned latent code distribution to match a prior distribution while the true distribution remains unknown. To improve the reconstruction quality and learn the latent space a manifold structure, this work present a novel approach using the adversarially approximated autoencoder (AAAE) to investigate the latent codes with adversarial approximation. Instead of regularizing the latent codes by penalizing on the distance between the distributions of the model and the target, AAAE learns the autoencoder flexibly and approximates the latent space with a simpler generator. The ratio is estimated using generative adversarial network (GAN) to enforce the similarity of the distributions. Additionally, the image space is regularized with an additional adversarial regularizer. The proposed approach unifies two deep generative models for both latent space inference and diverse generation. The learning scheme is realized without regularization on the latent codes, which also encourages faithful reconstruction. Extensive validation experiments on four real-world datasets demonstrate the superior performance of AAAE. In comparison to the state-of-the-art approaches, AAAE generates samples with better quality and shares the properties of regularized autoencoder with a nice latent manifold structure." @default.
- W2913735045 created "2019-02-21" @default.
- W2913735045 creator A5006497319 @default.
- W2913735045 creator A5031765917 @default.
- W2913735045 creator A5051094765 @default.
- W2913735045 date "2019-02-14" @default.
- W2913735045 modified "2023-09-24" @default.
- W2913735045 title "Adversarially Approximated Autoencoder for Image Generation and Manipulation" @default.
- W2913735045 cites W1834627138 @default.
- W2913735045 cites W1959608418 @default.
- W2913735045 cites W2099471712 @default.
- W2913735045 cites W2145094598 @default.
- W2913735045 cites W2163922914 @default.
- W2913735045 cites W2173520492 @default.
- W2913735045 cites W2217527616 @default.
- W2913735045 cites W2259677467 @default.
- W2913735045 cites W2411541852 @default.
- W2913735045 cites W2412320034 @default.
- W2913735045 cites W2519536754 @default.
- W2913735045 cites W2533598788 @default.
- W2913735045 cites W2559823555 @default.
- W2913735045 cites W2563587296 @default.
- W2913735045 cites W2585630030 @default.
- W2913735045 cites W2587284713 @default.
- W2913735045 cites W2592232824 @default.
- W2913735045 cites W2593768305 @default.
- W2913735045 cites W2594374979 @default.
- W2913735045 cites W2605195953 @default.
- W2913735045 cites W2621386477 @default.
- W2913735045 cites W2624872001 @default.
- W2913735045 cites W2735810033 @default.
- W2913735045 cites W2737047298 @default.
- W2913735045 cites W2739748921 @default.
- W2913735045 cites W2751076446 @default.
- W2913735045 cites W2757028014 @default.
- W2913735045 cites W2794284562 @default.
- W2913735045 cites W2804743778 @default.
- W2913735045 cites W2890930639 @default.
- W2913735045 cites W2903165770 @default.
- W2913735045 cites W2949899814 @default.
- W2913735045 cites W2949999304 @default.
- W2913735045 cites W2952673310 @default.
- W2913735045 cites W2962758212 @default.
- W2913735045 cites W2962793481 @default.
- W2913735045 cites W2962879692 @default.
- W2913735045 cites W2963021820 @default.
- W2913735045 cites W2963073614 @default.
- W2913735045 cites W2963090522 @default.
- W2913735045 cites W2963139417 @default.
- W2913735045 cites W2963142510 @default.
- W2913735045 cites W2963226019 @default.
- W2913735045 cites W2963330667 @default.
- W2913735045 cites W2963373786 @default.
- W2913735045 cites W2963470893 @default.
- W2913735045 cites W2963476931 @default.
- W2913735045 cites W2963592272 @default.
- W2913735045 cites W2963746531 @default.
- W2913735045 cites W2963981733 @default.
- W2913735045 cites W2964024144 @default.
- W2913735045 cites W2964121744 @default.
- W2913735045 cites W2964122153 @default.
- W2913735045 cites W2964167449 @default.
- W2913735045 cites W2964343746 @default.
- W2913735045 cites W3118608800 @default.
- W2913735045 cites W648143168 @default.
- W2913735045 doi "https://doi.org/10.48550/arxiv.1902.05581" @default.
- W2913735045 hasPublicationYear "2019" @default.
- W2913735045 type Work @default.
- W2913735045 sameAs 2913735045 @default.
- W2913735045 citedByCount "0" @default.
- W2913735045 crossrefType "posted-content" @default.
- W2913735045 hasAuthorship W2913735045A5006497319 @default.
- W2913735045 hasAuthorship W2913735045A5031765917 @default.
- W2913735045 hasAuthorship W2913735045A5051094765 @default.
- W2913735045 hasBestOaLocation W29137350451 @default.
- W2913735045 hasConcept C101738243 @default.
- W2913735045 hasConcept C107673813 @default.
- W2913735045 hasConcept C108583219 @default.
- W2913735045 hasConcept C11413529 @default.
- W2913735045 hasConcept C119857082 @default.
- W2913735045 hasConcept C127413603 @default.
- W2913735045 hasConcept C153180895 @default.
- W2913735045 hasConcept C154945302 @default.
- W2913735045 hasConcept C177769412 @default.
- W2913735045 hasConcept C2776135515 @default.
- W2913735045 hasConcept C2776214188 @default.
- W2913735045 hasConcept C33923547 @default.
- W2913735045 hasConcept C39890363 @default.
- W2913735045 hasConcept C41008148 @default.
- W2913735045 hasConcept C51167844 @default.
- W2913735045 hasConcept C529865628 @default.
- W2913735045 hasConcept C78519656 @default.
- W2913735045 hasConceptScore W2913735045C101738243 @default.
- W2913735045 hasConceptScore W2913735045C107673813 @default.
- W2913735045 hasConceptScore W2913735045C108583219 @default.
- W2913735045 hasConceptScore W2913735045C11413529 @default.
- W2913735045 hasConceptScore W2913735045C119857082 @default.
- W2913735045 hasConceptScore W2913735045C127413603 @default.
- W2913735045 hasConceptScore W2913735045C153180895 @default.
- W2913735045 hasConceptScore W2913735045C154945302 @default.