Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386814711> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4386814711 endingPage "10379" @default.
- W4386814711 startingPage "10379" @default.
- W4386814711 abstract "With the development of deep learning, image synthesis has achieved unprecedented achievements in the past few years. Image synthesis models, represented by diffusion models, demonstrated stable and high-fidelity image generation. However, the traditional diffusion model computes in pixel space, which is memory-heavy and computing-heavy. Therefore, to ease the expensive computing and improve the accessibility of diffusion models, we train the diffusion model in latent space. In this paper, we are devoted to creating novel paintings from existing paintings based on powerful diffusion models. Because the cross-attention layer is adopted in the latent diffusion model, we can create novel paintings with conditional text prompts. However, direct training of the diffusion model on the limited dataset is non-trivial. Therefore, inspired by the transfer learning, we train the diffusion model with the pre-trained weights, which eases the training process and enhances the image synthesis results. Additionally, we introduce the GPT-2 model to expand text prompts for detailed image generation. To validate the performance of our model, we train the model on paintings of the specific artist from the dataset WikiArt. To make up for missing image context descriptions of the WikiArt dataset, we adopt a pre-trained language model to generate corresponding context descriptions automatically and clean wrong descriptions manually, and we will make it available to the public. Experimental results demonstrate the capacity and effectiveness of the model." @default.
- W4386814711 created "2023-09-18" @default.
- W4386814711 creator A5017697475 @default.
- W4386814711 creator A5037496898 @default.
- W4386814711 creator A5051172458 @default.
- W4386814711 date "2023-09-16" @default.
- W4386814711 modified "2023-09-26" @default.
- W4386814711 title "Novel Paintings from the Latent Diffusion Model through Transfer Learning" @default.
- W4386814711 cites W2395579298 @default.
- W4386814711 cites W2962770929 @default.
- W4386814711 cites W3035574324 @default.
- W4386814711 cites W4312933868 @default.
- W4386814711 doi "https://doi.org/10.3390/app131810379" @default.
- W4386814711 hasPublicationYear "2023" @default.
- W4386814711 type Work @default.
- W4386814711 citedByCount "0" @default.
- W4386814711 crossrefType "journal-article" @default.
- W4386814711 hasAuthorship W4386814711A5017697475 @default.
- W4386814711 hasAuthorship W4386814711A5037496898 @default.
- W4386814711 hasAuthorship W4386814711A5051172458 @default.
- W4386814711 hasBestOaLocation W43868147111 @default.
- W4386814711 hasConcept C115961682 @default.
- W4386814711 hasConcept C119857082 @default.
- W4386814711 hasConcept C121332964 @default.
- W4386814711 hasConcept C142362112 @default.
- W4386814711 hasConcept C150899416 @default.
- W4386814711 hasConcept C151730666 @default.
- W4386814711 hasConcept C153349607 @default.
- W4386814711 hasConcept C154945302 @default.
- W4386814711 hasConcept C160633673 @default.
- W4386814711 hasConcept C199360897 @default.
- W4386814711 hasConcept C205783811 @default.
- W4386814711 hasConcept C2776459999 @default.
- W4386814711 hasConcept C2779343474 @default.
- W4386814711 hasConcept C41008148 @default.
- W4386814711 hasConcept C69357855 @default.
- W4386814711 hasConcept C76155785 @default.
- W4386814711 hasConcept C86803240 @default.
- W4386814711 hasConcept C97355855 @default.
- W4386814711 hasConcept C98045186 @default.
- W4386814711 hasConceptScore W4386814711C115961682 @default.
- W4386814711 hasConceptScore W4386814711C119857082 @default.
- W4386814711 hasConceptScore W4386814711C121332964 @default.
- W4386814711 hasConceptScore W4386814711C142362112 @default.
- W4386814711 hasConceptScore W4386814711C150899416 @default.
- W4386814711 hasConceptScore W4386814711C151730666 @default.
- W4386814711 hasConceptScore W4386814711C153349607 @default.
- W4386814711 hasConceptScore W4386814711C154945302 @default.
- W4386814711 hasConceptScore W4386814711C160633673 @default.
- W4386814711 hasConceptScore W4386814711C199360897 @default.
- W4386814711 hasConceptScore W4386814711C205783811 @default.
- W4386814711 hasConceptScore W4386814711C2776459999 @default.
- W4386814711 hasConceptScore W4386814711C2779343474 @default.
- W4386814711 hasConceptScore W4386814711C41008148 @default.
- W4386814711 hasConceptScore W4386814711C69357855 @default.
- W4386814711 hasConceptScore W4386814711C76155785 @default.
- W4386814711 hasConceptScore W4386814711C86803240 @default.
- W4386814711 hasConceptScore W4386814711C97355855 @default.
- W4386814711 hasConceptScore W4386814711C98045186 @default.
- W4386814711 hasIssue "18" @default.
- W4386814711 hasLocation W43868147111 @default.
- W4386814711 hasOpenAccess W4386814711 @default.
- W4386814711 hasPrimaryLocation W43868147111 @default.
- W4386814711 hasRelatedWork W2960456850 @default.
- W4386814711 hasRelatedWork W3015887428 @default.
- W4386814711 hasRelatedWork W3021430260 @default.
- W4386814711 hasRelatedWork W4281645081 @default.
- W4386814711 hasRelatedWork W4308262314 @default.
- W4386814711 hasRelatedWork W4312200629 @default.
- W4386814711 hasRelatedWork W4317565044 @default.
- W4386814711 hasRelatedWork W4362719745 @default.
- W4386814711 hasRelatedWork W4382286161 @default.
- W4386814711 hasRelatedWork W4386213806 @default.
- W4386814711 hasVolume "13" @default.
- W4386814711 isParatext "false" @default.
- W4386814711 isRetracted "false" @default.
- W4386814711 workType "article" @default.