Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770133182> ?p ?o ?g. }
- W2770133182 abstract "Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning. Variations of GAN have achieved competitive results on specific tasks. However, the stability of training and diversity of generated instances are still worth studying further. Training of GAN can be thought of as a greedy procedure, in which the generative net tries to make the locally optimal choice (minimizing loss function of discriminator) in each iteration. Unfortunately, this often makes generated data resemble only a few modes of real data and rotate between modes. To alleviate these problems, we propose a novel training strategy to restrict greed in training of GAN. With help of our method, the generated samples can cover more instance modes with more stable training process. Evaluating our method on several representative datasets, we demonstrate superiority of improved training strategy on typical GAN models with different distance metrics." @default.
- W2770133182 created "2017-12-04" @default.
- W2770133182 creator A5018863416 @default.
- W2770133182 creator A5049237773 @default.
- W2770133182 creator A5052716839 @default.
- W2770133182 creator A5056569344 @default.
- W2770133182 creator A5063626741 @default.
- W2770133182 creator A5084753767 @default.
- W2770133182 date "2017-11-28" @default.
- W2770133182 modified "2023-10-16" @default.
- W2770133182 title "Restricting Greed in Training of Generative Adversarial Network" @default.
- W2770133182 cites W1580389772 @default.
- W2770133182 cites W2099471712 @default.
- W2770133182 cites W2125389028 @default.
- W2770133182 cites W2173520492 @default.
- W2770133182 cites W2299565249 @default.
- W2770133182 cites W2312609093 @default.
- W2770133182 cites W2419501139 @default.
- W2770133182 cites W2432004435 @default.
- W2770133182 cites W2434741482 @default.
- W2770133182 cites W2521028896 @default.
- W2770133182 cites W2577946330 @default.
- W2770133182 cites W2581485081 @default.
- W2770133182 cites W2605195953 @default.
- W2770133182 cites W2605287558 @default.
- W2770133182 cites W2615429765 @default.
- W2770133182 cites W2619903301 @default.
- W2770133182 cites W2734402721 @default.
- W2770133182 cites W2751842161 @default.
- W2770133182 cites W2774049169 @default.
- W2770133182 cites W2949999304 @default.
- W2770133182 cites W2951004968 @default.
- W2770133182 cites W2951939904 @default.
- W2770133182 cites W2963470893 @default.
- W2770133182 cites W2964268978 @default.
- W2770133182 cites W3118608800 @default.
- W2770133182 doi "https://doi.org/10.48550/arxiv.1711.10152" @default.
- W2770133182 hasPublicationYear "2017" @default.
- W2770133182 type Work @default.
- W2770133182 sameAs 2770133182 @default.
- W2770133182 citedByCount "0" @default.
- W2770133182 crossrefType "posted-content" @default.
- W2770133182 hasAuthorship W2770133182A5018863416 @default.
- W2770133182 hasAuthorship W2770133182A5049237773 @default.
- W2770133182 hasAuthorship W2770133182A5052716839 @default.
- W2770133182 hasAuthorship W2770133182A5056569344 @default.
- W2770133182 hasAuthorship W2770133182A5063626741 @default.
- W2770133182 hasAuthorship W2770133182A5084753767 @default.
- W2770133182 hasBestOaLocation W27701331821 @default.
- W2770133182 hasConcept C111919701 @default.
- W2770133182 hasConcept C112972136 @default.
- W2770133182 hasConcept C119857082 @default.
- W2770133182 hasConcept C121332964 @default.
- W2770133182 hasConcept C127413603 @default.
- W2770133182 hasConcept C14036430 @default.
- W2770133182 hasConcept C144024400 @default.
- W2770133182 hasConcept C153294291 @default.
- W2770133182 hasConcept C154945302 @default.
- W2770133182 hasConcept C19165224 @default.
- W2770133182 hasConcept C202444582 @default.
- W2770133182 hasConcept C2777211547 @default.
- W2770133182 hasConcept C2779803651 @default.
- W2770133182 hasConcept C2780428219 @default.
- W2770133182 hasConcept C2781316041 @default.
- W2770133182 hasConcept C33923547 @default.
- W2770133182 hasConcept C37736160 @default.
- W2770133182 hasConcept C39890363 @default.
- W2770133182 hasConcept C41008148 @default.
- W2770133182 hasConcept C51632099 @default.
- W2770133182 hasConcept C76155785 @default.
- W2770133182 hasConcept C78458016 @default.
- W2770133182 hasConcept C78519656 @default.
- W2770133182 hasConcept C86803240 @default.
- W2770133182 hasConcept C94915269 @default.
- W2770133182 hasConcept C9652623 @default.
- W2770133182 hasConcept C98045186 @default.
- W2770133182 hasConceptScore W2770133182C111919701 @default.
- W2770133182 hasConceptScore W2770133182C112972136 @default.
- W2770133182 hasConceptScore W2770133182C119857082 @default.
- W2770133182 hasConceptScore W2770133182C121332964 @default.
- W2770133182 hasConceptScore W2770133182C127413603 @default.
- W2770133182 hasConceptScore W2770133182C14036430 @default.
- W2770133182 hasConceptScore W2770133182C144024400 @default.
- W2770133182 hasConceptScore W2770133182C153294291 @default.
- W2770133182 hasConceptScore W2770133182C154945302 @default.
- W2770133182 hasConceptScore W2770133182C19165224 @default.
- W2770133182 hasConceptScore W2770133182C202444582 @default.
- W2770133182 hasConceptScore W2770133182C2777211547 @default.
- W2770133182 hasConceptScore W2770133182C2779803651 @default.
- W2770133182 hasConceptScore W2770133182C2780428219 @default.
- W2770133182 hasConceptScore W2770133182C2781316041 @default.
- W2770133182 hasConceptScore W2770133182C33923547 @default.
- W2770133182 hasConceptScore W2770133182C37736160 @default.
- W2770133182 hasConceptScore W2770133182C39890363 @default.
- W2770133182 hasConceptScore W2770133182C41008148 @default.
- W2770133182 hasConceptScore W2770133182C51632099 @default.
- W2770133182 hasConceptScore W2770133182C76155785 @default.
- W2770133182 hasConceptScore W2770133182C78458016 @default.
- W2770133182 hasConceptScore W2770133182C78519656 @default.
- W2770133182 hasConceptScore W2770133182C86803240 @default.