Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297789460> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4297789460 abstract "Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit emphasis over high-frequency textural details of the images, and the difficulty to directly model the complex joint probability distribution over the high-dimensional image space. In this work, we approach these two challenges with a novel wavelet space VAE that uses the decoder to model the images in the wavelet coefficient space. This enables the VAE to emphasize over high-frequency components within an image obtained via wavelet decomposition. Additionally, by decomposing the complex function of generating high-dimensional images into inverse wavelet transformation and generation of wavelet coefficients, the latter becomes simpler to model by the VAE. We empirically validate that deep generative models operating in the wavelet space can generate images of higher quality than the image (RGB) space counterparts. Quantitatively, on benchmark natural image datasets, we achieve consistently better FID scores than VAE based architectures and competitive FID scores with a variety of GAN models for the same architectural and experimental setup. Furthermore, the proposed wavelet-based generative model retains desirable attributes like disentangled and informative latent representation without losing the quality in the generated samples." @default.
- W4297789460 created "2022-10-01" @default.
- W4297789460 creator A5008803380 @default.
- W4297789460 creator A5013815942 @default.
- W4297789460 creator A5045732749 @default.
- W4297789460 creator A5055063575 @default.
- W4297789460 creator A5062755809 @default.
- W4297789460 date "2019-10-26" @default.
- W4297789460 modified "2023-09-23" @default.
- W4297789460 title "Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models" @default.
- W4297789460 doi "https://doi.org/10.48550/arxiv.1911.05627" @default.
- W4297789460 hasPublicationYear "2019" @default.
- W4297789460 type Work @default.
- W4297789460 citedByCount "0" @default.
- W4297789460 crossrefType "posted-content" @default.
- W4297789460 hasAuthorship W4297789460A5008803380 @default.
- W4297789460 hasAuthorship W4297789460A5013815942 @default.
- W4297789460 hasAuthorship W4297789460A5045732749 @default.
- W4297789460 hasAuthorship W4297789460A5055063575 @default.
- W4297789460 hasAuthorship W4297789460A5062755809 @default.
- W4297789460 hasBestOaLocation W42977894601 @default.
- W4297789460 hasConcept C104317684 @default.
- W4297789460 hasConcept C13280743 @default.
- W4297789460 hasConcept C153180895 @default.
- W4297789460 hasConcept C154945302 @default.
- W4297789460 hasConcept C167966045 @default.
- W4297789460 hasConcept C185592680 @default.
- W4297789460 hasConcept C185798385 @default.
- W4297789460 hasConcept C204241405 @default.
- W4297789460 hasConcept C205649164 @default.
- W4297789460 hasConcept C33923547 @default.
- W4297789460 hasConcept C39890363 @default.
- W4297789460 hasConcept C41008148 @default.
- W4297789460 hasConcept C47432892 @default.
- W4297789460 hasConcept C51167844 @default.
- W4297789460 hasConcept C55493867 @default.
- W4297789460 hasConceptScore W4297789460C104317684 @default.
- W4297789460 hasConceptScore W4297789460C13280743 @default.
- W4297789460 hasConceptScore W4297789460C153180895 @default.
- W4297789460 hasConceptScore W4297789460C154945302 @default.
- W4297789460 hasConceptScore W4297789460C167966045 @default.
- W4297789460 hasConceptScore W4297789460C185592680 @default.
- W4297789460 hasConceptScore W4297789460C185798385 @default.
- W4297789460 hasConceptScore W4297789460C204241405 @default.
- W4297789460 hasConceptScore W4297789460C205649164 @default.
- W4297789460 hasConceptScore W4297789460C33923547 @default.
- W4297789460 hasConceptScore W4297789460C39890363 @default.
- W4297789460 hasConceptScore W4297789460C41008148 @default.
- W4297789460 hasConceptScore W4297789460C47432892 @default.
- W4297789460 hasConceptScore W4297789460C51167844 @default.
- W4297789460 hasConceptScore W4297789460C55493867 @default.
- W4297789460 hasLocation W42977894601 @default.
- W4297789460 hasOpenAccess W4297789460 @default.
- W4297789460 hasPrimaryLocation W42977894601 @default.
- W4297789460 hasRelatedWork W2148116311 @default.
- W4297789460 hasRelatedWork W2390972240 @default.
- W4297789460 hasRelatedWork W2541950815 @default.
- W4297789460 hasRelatedWork W2739734757 @default.
- W4297789460 hasRelatedWork W2786010873 @default.
- W4297789460 hasRelatedWork W3011817866 @default.
- W4297789460 hasRelatedWork W4288623594 @default.
- W4297789460 hasRelatedWork W4309969736 @default.
- W4297789460 hasRelatedWork W810659553 @default.
- W4297789460 hasRelatedWork W2898056092 @default.
- W4297789460 isParatext "false" @default.
- W4297789460 isRetracted "false" @default.
- W4297789460 workType "article" @default.