Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080394> ?p ?o ?g. }
- W4304080394 abstract "Generative adversarial networks (GANs) have demonstrated remarkable success in image synthesis applications, but their performance deteriorates under limited data regimes. The fundamental challenge is that it is extremely difficult to synthesize photo-realistic and highly diversified images while capturing meaningful attributes of the targets under minimum supervision. Previous methods either fine-tune or rewrite the model weights to adapt to few-shot datasets. However, this either overfits or requires access to large-scale data on which they are trained. To tackle the problem, we propose a framework that repurposes the existing pre-trained generative models using only a few samples (e.g., <30) of sketches. Unlike previous works, we transfer the sample diversity and quality without accessing the source data using inter-domain distance consistency. By employing cross-domain adversarial learning, we encourage the model output to closely resemble the input sketches in both shape and pose. Extensive experiments show that our method significantly outperforms the existing approaches in terms of sample quality and diversity. The qualitative and quantitative results on various standard datasets also demonstrate its efficacy. On the most popularly used dataset, Gabled church, we achieve a Fréchet inception distance (FID) score of 15.63." @default.
- W4304080394 created "2022-10-10" @default.
- W4304080394 creator A5052274720 @default.
- W4304080394 creator A5058405738 @default.
- W4304080394 date "2022-10-10" @default.
- W4304080394 modified "2023-09-28" @default.
- W4304080394 title "Customizing GAN Using Few-shot Sketches" @default.
- W4304080394 cites W2035652042 @default.
- W4304080394 cites W2050204708 @default.
- W4304080394 cites W2099684934 @default.
- W4304080394 cites W2108598243 @default.
- W4304080394 cites W2119381621 @default.
- W4304080394 cites W2149899758 @default.
- W4304080394 cites W2326925005 @default.
- W4304080394 cites W2331128040 @default.
- W4304080394 cites W2466618734 @default.
- W4304080394 cites W2467281799 @default.
- W4304080394 cites W2519536754 @default.
- W4304080394 cites W2593414223 @default.
- W4304080394 cites W2685669664 @default.
- W4304080394 cites W2962770929 @default.
- W4304080394 cites W2962793481 @default.
- W4304080394 cites W2962974533 @default.
- W4304080394 cites W2963073614 @default.
- W4304080394 cites W2963470893 @default.
- W4304080394 cites W2963636051 @default.
- W4304080394 cites W2963767194 @default.
- W4304080394 cites W2964105864 @default.
- W4304080394 cites W2982041717 @default.
- W4304080394 cites W2984648456 @default.
- W4304080394 cites W2985068832 @default.
- W4304080394 cites W2989855043 @default.
- W4304080394 cites W3035524453 @default.
- W4304080394 cites W3035574324 @default.
- W4304080394 cites W3043547428 @default.
- W4304080394 cites W3102061158 @default.
- W4304080394 cites W3174480022 @default.
- W4304080394 cites W3176913662 @default.
- W4304080394 cites W3177221875 @default.
- W4304080394 cites W3199674835 @default.
- W4304080394 cites W4214582496 @default.
- W4304080394 cites W4214926101 @default.
- W4304080394 doi "https://doi.org/10.1145/3503161.3548415" @default.
- W4304080394 hasPublicationYear "2022" @default.
- W4304080394 type Work @default.
- W4304080394 citedByCount "1" @default.
- W4304080394 countsByYear W43040803942023 @default.
- W4304080394 crossrefType "proceedings-article" @default.
- W4304080394 hasAuthorship W4304080394A5052274720 @default.
- W4304080394 hasAuthorship W4304080394A5058405738 @default.
- W4304080394 hasConcept C111472728 @default.
- W4304080394 hasConcept C115961682 @default.
- W4304080394 hasConcept C119857082 @default.
- W4304080394 hasConcept C124101348 @default.
- W4304080394 hasConcept C134306372 @default.
- W4304080394 hasConcept C138885662 @default.
- W4304080394 hasConcept C153180895 @default.
- W4304080394 hasConcept C154945302 @default.
- W4304080394 hasConcept C185592680 @default.
- W4304080394 hasConcept C198531522 @default.
- W4304080394 hasConcept C2776436953 @default.
- W4304080394 hasConcept C2779530757 @default.
- W4304080394 hasConcept C2988773926 @default.
- W4304080394 hasConcept C33923547 @default.
- W4304080394 hasConcept C36503486 @default.
- W4304080394 hasConcept C37736160 @default.
- W4304080394 hasConcept C39890363 @default.
- W4304080394 hasConcept C41008148 @default.
- W4304080394 hasConcept C43617362 @default.
- W4304080394 hasConceptScore W4304080394C111472728 @default.
- W4304080394 hasConceptScore W4304080394C115961682 @default.
- W4304080394 hasConceptScore W4304080394C119857082 @default.
- W4304080394 hasConceptScore W4304080394C124101348 @default.
- W4304080394 hasConceptScore W4304080394C134306372 @default.
- W4304080394 hasConceptScore W4304080394C138885662 @default.
- W4304080394 hasConceptScore W4304080394C153180895 @default.
- W4304080394 hasConceptScore W4304080394C154945302 @default.
- W4304080394 hasConceptScore W4304080394C185592680 @default.
- W4304080394 hasConceptScore W4304080394C198531522 @default.
- W4304080394 hasConceptScore W4304080394C2776436953 @default.
- W4304080394 hasConceptScore W4304080394C2779530757 @default.
- W4304080394 hasConceptScore W4304080394C2988773926 @default.
- W4304080394 hasConceptScore W4304080394C33923547 @default.
- W4304080394 hasConceptScore W4304080394C36503486 @default.
- W4304080394 hasConceptScore W4304080394C37736160 @default.
- W4304080394 hasConceptScore W4304080394C39890363 @default.
- W4304080394 hasConceptScore W4304080394C41008148 @default.
- W4304080394 hasConceptScore W4304080394C43617362 @default.
- W4304080394 hasLocation W43040803941 @default.
- W4304080394 hasOpenAccess W4304080394 @default.
- W4304080394 hasPrimaryLocation W43040803941 @default.
- W4304080394 hasRelatedWork W2901368259 @default.
- W4304080394 hasRelatedWork W3037184111 @default.
- W4304080394 hasRelatedWork W3156291593 @default.
- W4304080394 hasRelatedWork W3178813832 @default.
- W4304080394 hasRelatedWork W3198184493 @default.
- W4304080394 hasRelatedWork W4206598283 @default.
- W4304080394 hasRelatedWork W4220812973 @default.
- W4304080394 hasRelatedWork W4283579220 @default.
- W4304080394 hasRelatedWork W4312525628 @default.