Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202458081> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3202458081 endingPage "6771" @default.
- W3202458081 startingPage "6762" @default.
- W3202458081 abstract "Image generation has rapidly evolved in recent years. Modern architectures for adversarial training allow to generate even high resolution images with remarkable quality. At the same time, more and more effort is dedicated towards controlling the content of generated images. In this paper, we take one further step in this direction and propose a conditional generative adversarial network (GAN) that generates images with a defined number of objects from given classes. This entails two fundamental abilities (1) being able to generate high-quality images given a complex constraint and (2) being able to count object instances per class in a given image. Our proposed model modularly extends the successful StyleGAN2 architecture with a count-based conditioning as well as with a regression sub-network to count the number of generated objects per class during training. In experiments on three different datasets, we show that the proposed model learns to generate images according to the given multiple-class count condition even in the presence of complex backgrounds. In particular, we propose a new dataset, CityCount, which is derived from the Cityscapes street scenes dataset, to evaluate our approach in a challenging and practically relevant scenario." @default.
- W3202458081 created "2021-10-11" @default.
- W3202458081 creator A5029656834 @default.
- W3202458081 creator A5065718385 @default.
- W3202458081 creator A5079433058 @default.
- W3202458081 date "2021-01-01" @default.
- W3202458081 modified "2023-09-27" @default.
- W3202458081 title "Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation" @default.
- W3202458081 hasPublicationYear "2021" @default.
- W3202458081 type Work @default.
- W3202458081 sameAs 3202458081 @default.
- W3202458081 citedByCount "0" @default.
- W3202458081 crossrefType "proceedings-article" @default.
- W3202458081 hasAuthorship W3202458081A5029656834 @default.
- W3202458081 hasAuthorship W3202458081A5065718385 @default.
- W3202458081 hasAuthorship W3202458081A5079433058 @default.
- W3202458081 hasConcept C111472728 @default.
- W3202458081 hasConcept C115961682 @default.
- W3202458081 hasConcept C119857082 @default.
- W3202458081 hasConcept C138885662 @default.
- W3202458081 hasConcept C153180895 @default.
- W3202458081 hasConcept C154945302 @default.
- W3202458081 hasConcept C2524010 @default.
- W3202458081 hasConcept C2776036281 @default.
- W3202458081 hasConcept C2777212361 @default.
- W3202458081 hasConcept C2779530757 @default.
- W3202458081 hasConcept C2779757391 @default.
- W3202458081 hasConcept C2781238097 @default.
- W3202458081 hasConcept C31972630 @default.
- W3202458081 hasConcept C33923547 @default.
- W3202458081 hasConcept C37736160 @default.
- W3202458081 hasConcept C41008148 @default.
- W3202458081 hasConceptScore W3202458081C111472728 @default.
- W3202458081 hasConceptScore W3202458081C115961682 @default.
- W3202458081 hasConceptScore W3202458081C119857082 @default.
- W3202458081 hasConceptScore W3202458081C138885662 @default.
- W3202458081 hasConceptScore W3202458081C153180895 @default.
- W3202458081 hasConceptScore W3202458081C154945302 @default.
- W3202458081 hasConceptScore W3202458081C2524010 @default.
- W3202458081 hasConceptScore W3202458081C2776036281 @default.
- W3202458081 hasConceptScore W3202458081C2777212361 @default.
- W3202458081 hasConceptScore W3202458081C2779530757 @default.
- W3202458081 hasConceptScore W3202458081C2779757391 @default.
- W3202458081 hasConceptScore W3202458081C2781238097 @default.
- W3202458081 hasConceptScore W3202458081C31972630 @default.
- W3202458081 hasConceptScore W3202458081C33923547 @default.
- W3202458081 hasConceptScore W3202458081C37736160 @default.
- W3202458081 hasConceptScore W3202458081C41008148 @default.
- W3202458081 hasLocation W32024580811 @default.
- W3202458081 hasOpenAccess W3202458081 @default.
- W3202458081 hasPrimaryLocation W32024580811 @default.
- W3202458081 hasRelatedWork W1595095002 @default.
- W3202458081 hasRelatedWork W2261268509 @default.
- W3202458081 hasRelatedWork W2595519089 @default.
- W3202458081 hasRelatedWork W2603089249 @default.
- W3202458081 hasRelatedWork W2624258464 @default.
- W3202458081 hasRelatedWork W2896317337 @default.
- W3202458081 hasRelatedWork W2899034697 @default.
- W3202458081 hasRelatedWork W2962519558 @default.
- W3202458081 hasRelatedWork W2980574649 @default.
- W3202458081 hasRelatedWork W2988398572 @default.
- W3202458081 hasRelatedWork W2998468066 @default.
- W3202458081 hasRelatedWork W3009854368 @default.
- W3202458081 hasRelatedWork W3025348309 @default.
- W3202458081 hasRelatedWork W3036751501 @default.
- W3202458081 hasRelatedWork W3099495704 @default.
- W3202458081 hasRelatedWork W3120979957 @default.
- W3202458081 hasRelatedWork W3142813729 @default.
- W3202458081 hasRelatedWork W3187515119 @default.
- W3202458081 hasRelatedWork W3204731714 @default.
- W3202458081 hasRelatedWork W998260344 @default.
- W3202458081 isParatext "false" @default.
- W3202458081 isRetracted "false" @default.
- W3202458081 magId "3202458081" @default.
- W3202458081 workType "article" @default.