Matches in SemOpenAlex for { <https://semopenalex.org/work/W3112543861> ?p ?o ?g. }
- W3112543861 abstract "Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. As it is unreasonable to expect to fully infer the distribution from just a few observations (e.g., emojis), we seek to leverage a large, related source domain as pretraining (e.g., human faces). Thus, we wish to preserve the diversity of the source domain, while adapting to the appearance of the target. We adapt a pretrained model, without introducing any additional parameters, to the few examples of the target domain. Crucially, we regularize the changes of the weights during this adaptation, in order to best preserve the information of the source dataset, while fitting the target. We demonstrate the effectiveness of our algorithm by generating high-quality results of different target domains, including those with extremely few examples (e.g., <10). We also analyze the performance of our method with respect to some important factors, such as the number of examples and the dissimilarity between the source and target domain." @default.
- W3112543861 created "2020-12-21" @default.
- W3112543861 creator A5024777042 @default.
- W3112543861 creator A5032039152 @default.
- W3112543861 creator A5081018103 @default.
- W3112543861 creator A5085050428 @default.
- W3112543861 date "2020-12-04" @default.
- W3112543861 modified "2023-09-23" @default.
- W3112543861 title "Few-shot Image Generation with Elastic Weight Consolidation" @default.
- W3112543861 cites W1834627138 @default.
- W3112543861 cites W2099471712 @default.
- W3112543861 cites W2117539524 @default.
- W3112543861 cites W2173520492 @default.
- W3112543861 cites W2194321275 @default.
- W3112543861 cites W2292976057 @default.
- W3112543861 cites W2331128040 @default.
- W3112543861 cites W2475287302 @default.
- W3112543861 cites W2553897675 @default.
- W3112543861 cites W2560647685 @default.
- W3112543861 cites W2564726951 @default.
- W3112543861 cites W2601450892 @default.
- W3112543861 cites W2603777577 @default.
- W3112543861 cites W2604763608 @default.
- W3112543861 cites W2619508703 @default.
- W3112543861 cites W2737492962 @default.
- W3112543861 cites W2766669584 @default.
- W3112543861 cites W2783879794 @default.
- W3112543861 cites W2794857359 @default.
- W3112543861 cites W2795900505 @default.
- W3112543861 cites W2798836702 @default.
- W3112543861 cites W2799854879 @default.
- W3112543861 cites W2891707612 @default.
- W3112543861 cites W2893749619 @default.
- W3112543861 cites W2942626212 @default.
- W3112543861 cites W2949247522 @default.
- W3112543861 cites W2961310105 @default.
- W3112543861 cites W2962724315 @default.
- W3112543861 cites W2962760235 @default.
- W3112543861 cites W2962770929 @default.
- W3112543861 cites W2962772087 @default.
- W3112543861 cites W2962793481 @default.
- W3112543861 cites W2962860923 @default.
- W3112543861 cites W2963073614 @default.
- W3112543861 cites W2963330667 @default.
- W3112543861 cites W2963341924 @default.
- W3112543861 cites W2963652345 @default.
- W3112543861 cites W2963683323 @default.
- W3112543861 cites W2963813679 @default.
- W3112543861 cites W2963981733 @default.
- W3112543861 cites W2964155733 @default.
- W3112543861 cites W2984648456 @default.
- W3112543861 cites W2990452356 @default.
- W3112543861 cites W3021931813 @default.
- W3112543861 cites W3034577585 @default.
- W3112543861 cites W3034600949 @default.
- W3112543861 cites W3034855543 @default.
- W3112543861 cites W648143168 @default.
- W3112543861 hasPublicationYear "2020" @default.
- W3112543861 type Work @default.
- W3112543861 sameAs 3112543861 @default.
- W3112543861 citedByCount "0" @default.
- W3112543861 crossrefType "posted-content" @default.
- W3112543861 hasAuthorship W3112543861A5024777042 @default.
- W3112543861 hasAuthorship W3112543861A5032039152 @default.
- W3112543861 hasAuthorship W3112543861A5081018103 @default.
- W3112543861 hasAuthorship W3112543861A5085050428 @default.
- W3112543861 hasConcept C11413529 @default.
- W3112543861 hasConcept C115961682 @default.
- W3112543861 hasConcept C119857082 @default.
- W3112543861 hasConcept C121955636 @default.
- W3112543861 hasConcept C124101348 @default.
- W3112543861 hasConcept C134306372 @default.
- W3112543861 hasConcept C144133560 @default.
- W3112543861 hasConcept C153083717 @default.
- W3112543861 hasConcept C153180895 @default.
- W3112543861 hasConcept C154945302 @default.
- W3112543861 hasConcept C2776014549 @default.
- W3112543861 hasConcept C2776434776 @default.
- W3112543861 hasConcept C31972630 @default.
- W3112543861 hasConcept C33923547 @default.
- W3112543861 hasConcept C36503486 @default.
- W3112543861 hasConcept C41008148 @default.
- W3112543861 hasConcept C95623464 @default.
- W3112543861 hasConceptScore W3112543861C11413529 @default.
- W3112543861 hasConceptScore W3112543861C115961682 @default.
- W3112543861 hasConceptScore W3112543861C119857082 @default.
- W3112543861 hasConceptScore W3112543861C121955636 @default.
- W3112543861 hasConceptScore W3112543861C124101348 @default.
- W3112543861 hasConceptScore W3112543861C134306372 @default.
- W3112543861 hasConceptScore W3112543861C144133560 @default.
- W3112543861 hasConceptScore W3112543861C153083717 @default.
- W3112543861 hasConceptScore W3112543861C153180895 @default.
- W3112543861 hasConceptScore W3112543861C154945302 @default.
- W3112543861 hasConceptScore W3112543861C2776014549 @default.
- W3112543861 hasConceptScore W3112543861C2776434776 @default.
- W3112543861 hasConceptScore W3112543861C31972630 @default.
- W3112543861 hasConceptScore W3112543861C33923547 @default.
- W3112543861 hasConceptScore W3112543861C36503486 @default.
- W3112543861 hasConceptScore W3112543861C41008148 @default.
- W3112543861 hasConceptScore W3112543861C95623464 @default.