Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313000281> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4313000281 endingPage "364" @default.
- W4313000281 startingPage "352" @default.
- W4313000281 abstract "Conditional Generative Adversarial Networks (CGANs) are diversely utilized for data synthesis in applied sciences and natural image tasks. Conditional generative models extend upon data generation to account for labeled data by estimating joint distributions of samples and labels. We present a family of modified CGANs which demonstrate the inclusion of reconstructive cycles between prior and data spaces inspired by BiGAN and CycleGAN improves upon baselines for natural image synthesis with three primary contributions. The first is a study proposing three incremental architectures for conditional data generation which demonstrate improvement on baseline generation quality for a natural image data set across multiple generative metrics. The second is a novel approach to structure latent representations by learning a paired structured condition space and weakly structured variation space with desirable sampling and supervised learning properties. The third is a proposed utilization of conditional image synthesis for supervised learner data set augmentation as an alternative generation metric. Additional experiments demonstrate the successes of inducing cycles in conditional GANs for both image synthesis and image classification over comparable models with no additional tweaks or modifications. We release our source code, models, and experiments here: https://github.com/alexander-moore/Cycles-Improve-Conditional-Generators ." @default.
- W4313000281 created "2023-01-05" @default.
- W4313000281 creator A5009300007 @default.
- W4313000281 creator A5027655988 @default.
- W4313000281 creator A5059652073 @default.
- W4313000281 creator A5080522896 @default.
- W4313000281 date "2022-01-01" @default.
- W4313000281 modified "2023-09-30" @default.
- W4313000281 title "Cycles Improve Conditional Generators: Synthesis and Augmentation for Data Mining" @default.
- W4313000281 cites W2183341477 @default.
- W4313000281 cites W2962793481 @default.
- W4313000281 cites W4221163508 @default.
- W4313000281 doi "https://doi.org/10.1007/978-3-031-22137-8_26" @default.
- W4313000281 hasPublicationYear "2022" @default.
- W4313000281 type Work @default.
- W4313000281 citedByCount "0" @default.
- W4313000281 crossrefType "book-chapter" @default.
- W4313000281 hasAuthorship W4313000281A5009300007 @default.
- W4313000281 hasAuthorship W4313000281A5027655988 @default.
- W4313000281 hasAuthorship W4313000281A5059652073 @default.
- W4313000281 hasAuthorship W4313000281A5080522896 @default.
- W4313000281 hasConcept C105795698 @default.
- W4313000281 hasConcept C106131492 @default.
- W4313000281 hasConcept C115961682 @default.
- W4313000281 hasConcept C119857082 @default.
- W4313000281 hasConcept C124101348 @default.
- W4313000281 hasConcept C140779682 @default.
- W4313000281 hasConcept C153180895 @default.
- W4313000281 hasConcept C154945302 @default.
- W4313000281 hasConcept C160920958 @default.
- W4313000281 hasConcept C162324750 @default.
- W4313000281 hasConcept C167966045 @default.
- W4313000281 hasConcept C176217482 @default.
- W4313000281 hasConcept C177264268 @default.
- W4313000281 hasConcept C199360897 @default.
- W4313000281 hasConcept C21547014 @default.
- W4313000281 hasConcept C2776760102 @default.
- W4313000281 hasConcept C2989087649 @default.
- W4313000281 hasConcept C31972630 @default.
- W4313000281 hasConcept C33923547 @default.
- W4313000281 hasConcept C39890363 @default.
- W4313000281 hasConcept C41008148 @default.
- W4313000281 hasConcept C43555835 @default.
- W4313000281 hasConcept C51167844 @default.
- W4313000281 hasConcept C58489278 @default.
- W4313000281 hasConceptScore W4313000281C105795698 @default.
- W4313000281 hasConceptScore W4313000281C106131492 @default.
- W4313000281 hasConceptScore W4313000281C115961682 @default.
- W4313000281 hasConceptScore W4313000281C119857082 @default.
- W4313000281 hasConceptScore W4313000281C124101348 @default.
- W4313000281 hasConceptScore W4313000281C140779682 @default.
- W4313000281 hasConceptScore W4313000281C153180895 @default.
- W4313000281 hasConceptScore W4313000281C154945302 @default.
- W4313000281 hasConceptScore W4313000281C160920958 @default.
- W4313000281 hasConceptScore W4313000281C162324750 @default.
- W4313000281 hasConceptScore W4313000281C167966045 @default.
- W4313000281 hasConceptScore W4313000281C176217482 @default.
- W4313000281 hasConceptScore W4313000281C177264268 @default.
- W4313000281 hasConceptScore W4313000281C199360897 @default.
- W4313000281 hasConceptScore W4313000281C21547014 @default.
- W4313000281 hasConceptScore W4313000281C2776760102 @default.
- W4313000281 hasConceptScore W4313000281C2989087649 @default.
- W4313000281 hasConceptScore W4313000281C31972630 @default.
- W4313000281 hasConceptScore W4313000281C33923547 @default.
- W4313000281 hasConceptScore W4313000281C39890363 @default.
- W4313000281 hasConceptScore W4313000281C41008148 @default.
- W4313000281 hasConceptScore W4313000281C43555835 @default.
- W4313000281 hasConceptScore W4313000281C51167844 @default.
- W4313000281 hasConceptScore W4313000281C58489278 @default.
- W4313000281 hasLocation W43130002811 @default.
- W4313000281 hasOpenAccess W4313000281 @default.
- W4313000281 hasPrimaryLocation W43130002811 @default.
- W4313000281 hasRelatedWork W2786010873 @default.
- W4313000281 hasRelatedWork W2790214987 @default.
- W4313000281 hasRelatedWork W2963529210 @default.
- W4313000281 hasRelatedWork W3112062303 @default.
- W4313000281 hasRelatedWork W3137809915 @default.
- W4313000281 hasRelatedWork W4226016476 @default.
- W4313000281 hasRelatedWork W4293659211 @default.
- W4313000281 hasRelatedWork W4317211522 @default.
- W4313000281 hasRelatedWork W4362665278 @default.
- W4313000281 hasRelatedWork W4378422443 @default.
- W4313000281 isParatext "false" @default.
- W4313000281 isRetracted "false" @default.
- W4313000281 workType "book-chapter" @default.