Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896798715> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2896798715 abstract "In recent years, Generative Adversarial Networks (GANs) have shown substantial progress in modeling complex distributions of data. These networks have received tremendous attention since they can generate implicit probabilistic models that produce realistic data using a stochastic procedure. While such models have proven highly effective in diverse scenarios, they require a large set of fully-observed training samples. In many applications access to such samples are difficult or even impractical and only noisy or partial observations of the desired distribution is available. Recent research has tried to address the problem of incompletely observed samples to recover the distribution of the data. citep{zhu2017unpaired} and citep{yeh2016semantic} proposed methods to solve ill-posed inverse problem using cycle-consistency and latent-space mappings in adversarial networks, respectively. citep{bora2017compressed} and citep{kabkab2018task} have applied similar adversarial approaches to the problem of compressed sensing. In this work, we focus on a new variant of GAN models called AmbientGAN, which incorporates a measurement process (e.g. adding noise, data removal and projection) into the GAN training. While in the standard GAN, the discriminator distinguishes a generated image from a real image, in AmbientGAN model the discriminator has to separate a real measurement from a simulated measurement of a generated image. The results shown by citep{bora2018ambientgan} are quite promising for the problem of incomplete data, and have potentially important implications for generative approaches to compressed sensing and ill-posed problems." @default.
- W2896798715 created "2018-10-26" @default.
- W2896798715 creator A5020232391 @default.
- W2896798715 creator A5027011074 @default.
- W2896798715 creator A5051592642 @default.
- W2896798715 creator A5081515598 @default.
- W2896798715 date "2018-10-23" @default.
- W2896798715 modified "2023-09-26" @default.
- W2896798715 title "Reproducing AmbientGAN: Generative models from lossy measurements" @default.
- W2896798715 cites W2173520492 @default.
- W2896798715 cites W2479644247 @default.
- W2896798715 cites W2605287558 @default.
- W2896798715 cites W2786277362 @default.
- W2896798715 cites W2949536516 @default.
- W2896798715 hasPublicationYear "2018" @default.
- W2896798715 type Work @default.
- W2896798715 sameAs 2896798715 @default.
- W2896798715 citedByCount "0" @default.
- W2896798715 crossrefType "posted-content" @default.
- W2896798715 hasAuthorship W2896798715A5020232391 @default.
- W2896798715 hasAuthorship W2896798715A5027011074 @default.
- W2896798715 hasAuthorship W2896798715A5051592642 @default.
- W2896798715 hasAuthorship W2896798715A5081515598 @default.
- W2896798715 hasConcept C11413529 @default.
- W2896798715 hasConcept C134306372 @default.
- W2896798715 hasConcept C135252773 @default.
- W2896798715 hasConcept C154945302 @default.
- W2896798715 hasConcept C165021410 @default.
- W2896798715 hasConcept C2779803651 @default.
- W2896798715 hasConcept C33923547 @default.
- W2896798715 hasConcept C39890363 @default.
- W2896798715 hasConcept C41008148 @default.
- W2896798715 hasConcept C49937458 @default.
- W2896798715 hasConcept C76155785 @default.
- W2896798715 hasConcept C80444323 @default.
- W2896798715 hasConcept C94915269 @default.
- W2896798715 hasConceptScore W2896798715C11413529 @default.
- W2896798715 hasConceptScore W2896798715C134306372 @default.
- W2896798715 hasConceptScore W2896798715C135252773 @default.
- W2896798715 hasConceptScore W2896798715C154945302 @default.
- W2896798715 hasConceptScore W2896798715C165021410 @default.
- W2896798715 hasConceptScore W2896798715C2779803651 @default.
- W2896798715 hasConceptScore W2896798715C33923547 @default.
- W2896798715 hasConceptScore W2896798715C39890363 @default.
- W2896798715 hasConceptScore W2896798715C41008148 @default.
- W2896798715 hasConceptScore W2896798715C49937458 @default.
- W2896798715 hasConceptScore W2896798715C76155785 @default.
- W2896798715 hasConceptScore W2896798715C80444323 @default.
- W2896798715 hasConceptScore W2896798715C94915269 @default.
- W2896798715 hasLocation W28967987151 @default.
- W2896798715 hasOpenAccess W2896798715 @default.
- W2896798715 hasPrimaryLocation W28967987151 @default.
- W2896798715 hasRelatedWork W2184746145 @default.
- W2896798715 hasRelatedWork W2469599570 @default.
- W2896798715 hasRelatedWork W2761173574 @default.
- W2896798715 hasRelatedWork W2787682597 @default.
- W2896798715 hasRelatedWork W2788766568 @default.
- W2896798715 hasRelatedWork W2804184144 @default.
- W2896798715 hasRelatedWork W2885442750 @default.
- W2896798715 hasRelatedWork W2943930307 @default.
- W2896798715 hasRelatedWork W2949342585 @default.
- W2896798715 hasRelatedWork W2951684903 @default.
- W2896798715 hasRelatedWork W2963031612 @default.
- W2896798715 hasRelatedWork W2963864522 @default.
- W2896798715 hasRelatedWork W2964850033 @default.
- W2896798715 hasRelatedWork W2965141076 @default.
- W2896798715 hasRelatedWork W3025658083 @default.
- W2896798715 hasRelatedWork W3098020164 @default.
- W2896798715 hasRelatedWork W3112010404 @default.
- W2896798715 hasRelatedWork W3117902544 @default.
- W2896798715 hasRelatedWork W3209284864 @default.
- W2896798715 hasRelatedWork W3213492739 @default.
- W2896798715 isParatext "false" @default.
- W2896798715 isRetracted "false" @default.
- W2896798715 magId "2896798715" @default.
- W2896798715 workType "article" @default.