Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312898060> ?p ?o ?g. }
- W4312898060 endingPage "249" @default.
- W4312898060 startingPage "235" @default.
- W4312898060 abstract "Image-to-image translation is the recent trend to transform images from one domain to another domain using a generative adversarial network (GAN). The existing GAN models perform the training by only utilizing the input and output modalities of transformation. In this paper, we perform the semantic injected training of GAN models. Specifically, we train with original input and output modalities and inject a few epochs of training for translation from input to semantic map. Let us refer to the original training as the training for the translation of the input image into the target domain. The injection of semantic training in the original training improves the generalization capability of the trained GAN model. Moreover, it also preserves the categorical information in a better way in the generated image. The semantic map is only utilized at the training time and is not required at the test time. The experiments are performed using state-of-the-art GAN models over CityScapes and RGB-NIR stereo datasets. We observe the improved performance in terms of the SSIM, FID, and KID scores after injecting semantic training as compared to the original training." @default.
- W4312898060 created "2023-01-05" @default.
- W4312898060 creator A5000923040 @default.
- W4312898060 creator A5021725191 @default.
- W4312898060 creator A5041368976 @default.
- W4312898060 creator A5048082929 @default.
- W4312898060 creator A5055226266 @default.
- W4312898060 creator A5083245037 @default.
- W4312898060 creator A5090155483 @default.
- W4312898060 date "2022-01-01" @default.
- W4312898060 modified "2023-10-02" @default.
- W4312898060 title "Semantic Map Injected GAN Training for Image-to-Image Translation" @default.
- W4312898060 cites W2194775991 @default.
- W4312898060 cites W2300779272 @default.
- W4312898060 cites W2326925005 @default.
- W4312898060 cites W2593414223 @default.
- W4312898060 cites W2794022343 @default.
- W4312898060 cites W2798956329 @default.
- W4312898060 cites W2806118840 @default.
- W4312898060 cites W2919115771 @default.
- W4312898060 cites W2949983948 @default.
- W4312898060 cites W2956776104 @default.
- W4312898060 cites W2962793481 @default.
- W4312898060 cites W2963073614 @default.
- W4312898060 cites W2963444790 @default.
- W4312898060 cites W2963466847 @default.
- W4312898060 cites W2963649420 @default.
- W4312898060 cites W2964125246 @default.
- W4312898060 cites W2981515171 @default.
- W4312898060 cites W2991651424 @default.
- W4312898060 cites W3034832575 @default.
- W4312898060 cites W3035398999 @default.
- W4312898060 cites W3039655629 @default.
- W4312898060 cites W3101156210 @default.
- W4312898060 cites W3105654374 @default.
- W4312898060 cites W3108274592 @default.
- W4312898060 cites W3108316907 @default.
- W4312898060 cites W3113141251 @default.
- W4312898060 cites W3128861763 @default.
- W4312898060 cites W3165204504 @default.
- W4312898060 cites W4230012894 @default.
- W4312898060 doi "https://doi.org/10.1007/978-981-19-4136-8_16" @default.
- W4312898060 hasPublicationYear "2022" @default.
- W4312898060 type Work @default.
- W4312898060 citedByCount "1" @default.
- W4312898060 countsByYear W43128980602023 @default.
- W4312898060 crossrefType "book-chapter" @default.
- W4312898060 hasAuthorship W4312898060A5000923040 @default.
- W4312898060 hasAuthorship W4312898060A5021725191 @default.
- W4312898060 hasAuthorship W4312898060A5041368976 @default.
- W4312898060 hasAuthorship W4312898060A5048082929 @default.
- W4312898060 hasAuthorship W4312898060A5055226266 @default.
- W4312898060 hasAuthorship W4312898060A5083245037 @default.
- W4312898060 hasAuthorship W4312898060A5090155483 @default.
- W4312898060 hasBestOaLocation W43128980602 @default.
- W4312898060 hasConcept C104317684 @default.
- W4312898060 hasConcept C105580179 @default.
- W4312898060 hasConcept C115961682 @default.
- W4312898060 hasConcept C119857082 @default.
- W4312898060 hasConcept C121332964 @default.
- W4312898060 hasConcept C134306372 @default.
- W4312898060 hasConcept C144024400 @default.
- W4312898060 hasConcept C149364088 @default.
- W4312898060 hasConcept C153180895 @default.
- W4312898060 hasConcept C153294291 @default.
- W4312898060 hasConcept C154945302 @default.
- W4312898060 hasConcept C177148314 @default.
- W4312898060 hasConcept C185592680 @default.
- W4312898060 hasConcept C204241405 @default.
- W4312898060 hasConcept C2777211547 @default.
- W4312898060 hasConcept C2779757391 @default.
- W4312898060 hasConcept C2779903281 @default.
- W4312898060 hasConcept C31972630 @default.
- W4312898060 hasConcept C33923547 @default.
- W4312898060 hasConcept C36289849 @default.
- W4312898060 hasConcept C36503486 @default.
- W4312898060 hasConcept C41008148 @default.
- W4312898060 hasConcept C50644808 @default.
- W4312898060 hasConcept C5274069 @default.
- W4312898060 hasConcept C55493867 @default.
- W4312898060 hasConcept C82990744 @default.
- W4312898060 hasConceptScore W4312898060C104317684 @default.
- W4312898060 hasConceptScore W4312898060C105580179 @default.
- W4312898060 hasConceptScore W4312898060C115961682 @default.
- W4312898060 hasConceptScore W4312898060C119857082 @default.
- W4312898060 hasConceptScore W4312898060C121332964 @default.
- W4312898060 hasConceptScore W4312898060C134306372 @default.
- W4312898060 hasConceptScore W4312898060C144024400 @default.
- W4312898060 hasConceptScore W4312898060C149364088 @default.
- W4312898060 hasConceptScore W4312898060C153180895 @default.
- W4312898060 hasConceptScore W4312898060C153294291 @default.
- W4312898060 hasConceptScore W4312898060C154945302 @default.
- W4312898060 hasConceptScore W4312898060C177148314 @default.
- W4312898060 hasConceptScore W4312898060C185592680 @default.
- W4312898060 hasConceptScore W4312898060C204241405 @default.
- W4312898060 hasConceptScore W4312898060C2777211547 @default.
- W4312898060 hasConceptScore W4312898060C2779757391 @default.
- W4312898060 hasConceptScore W4312898060C2779903281 @default.