Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293146040> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4293146040 endingPage "317" @default.
- W4293146040 startingPage "306" @default.
- W4293146040 abstract "Semantic Inpainting on Segmentation Map (SISM) aims to manipulate segmentation maps by semantics. Recent works show SISM provides semantic-aware auxiliary information for better style or structure manipulations. Providing structural assistance, segmentation maps have been broadly used as an intermediate interface to achieve better image manipulation. Mainstream solutions of image manipulation use Generative Adversarial Net (GAN) globally, locally or jointly. It is also applicable to SISM. However, the discriminator of global GAN is easier fooled, because the majority of its input is the same as the ground-truth, which is hard to fully mitigate the inconsistency between inpainted areas and the context. The inconsistency is more difficult for local GAN to address, due to the lack of context in its input. To mitigate the inconsistency, we propose a novel Multi-Expansion (MEx) loss. It is implemented by the adversarial loss on MEx areas. Each MEx area has the inpainted area as dominance and keeps knowledge of the scene context, so the consistency of the SISM results can be boosted. We propose an approximation of MEx loss, i.e., A-MEx loss, to further enhance the stability and usability. Besides performing well on SISM tasks, MEx loss also performs impressively on natural image inpainting. Extensive experiments on the two tasks demonstrate the advantages of our model over existing methods on four challenging datasets, such as a 2.59% increase in Hamm on SISM in Cityscape and a decrease of 5.00% FID on natural image inpainting in CMP Facade. The code of our work is available at: https://github.com/he159ok/AMEx-MEx-Loss." @default.
- W4293146040 created "2022-08-27" @default.
- W4293146040 creator A5034112897 @default.
- W4293146040 creator A5034757629 @default.
- W4293146040 creator A5038002204 @default.
- W4293146040 creator A5062082438 @default.
- W4293146040 creator A5074151953 @default.
- W4293146040 creator A5088099909 @default.
- W4293146040 date "2022-08-01" @default.
- W4293146040 modified "2023-10-14" @default.
- W4293146040 title "Semantic inpainting on segmentation map via multi-expansion loss" @default.
- W4293146040 cites W1796263212 @default.
- W4293146040 cites W1861492603 @default.
- W4293146040 cites W2133665775 @default.
- W4293146040 cites W2560481159 @default.
- W4293146040 cites W2735680049 @default.
- W4293146040 cites W2738588019 @default.
- W4293146040 cites W2963561004 @default.
- W4293146040 cites W2964082390 @default.
- W4293146040 cites W2964118024 @default.
- W4293146040 cites W2964252316 @default.
- W4293146040 cites W2986945954 @default.
- W4293146040 cites W3002107777 @default.
- W4293146040 cites W3003860948 @default.
- W4293146040 cites W3035231706 @default.
- W4293146040 cites W3106333289 @default.
- W4293146040 cites W3106725490 @default.
- W4293146040 cites W3122887115 @default.
- W4293146040 doi "https://doi.org/10.1016/j.neucom.2022.06.025" @default.
- W4293146040 hasPublicationYear "2022" @default.
- W4293146040 type Work @default.
- W4293146040 citedByCount "1" @default.
- W4293146040 crossrefType "journal-article" @default.
- W4293146040 hasAuthorship W4293146040A5034112897 @default.
- W4293146040 hasAuthorship W4293146040A5034757629 @default.
- W4293146040 hasAuthorship W4293146040A5038002204 @default.
- W4293146040 hasAuthorship W4293146040A5062082438 @default.
- W4293146040 hasAuthorship W4293146040A5074151953 @default.
- W4293146040 hasAuthorship W4293146040A5088099909 @default.
- W4293146040 hasConcept C115961682 @default.
- W4293146040 hasConcept C11727466 @default.
- W4293146040 hasConcept C146849305 @default.
- W4293146040 hasConcept C151730666 @default.
- W4293146040 hasConcept C154945302 @default.
- W4293146040 hasConcept C177264268 @default.
- W4293146040 hasConcept C184337299 @default.
- W4293146040 hasConcept C199360897 @default.
- W4293146040 hasConcept C2776760102 @default.
- W4293146040 hasConcept C2779343474 @default.
- W4293146040 hasConcept C2779803651 @default.
- W4293146040 hasConcept C31972630 @default.
- W4293146040 hasConcept C41008148 @default.
- W4293146040 hasConcept C76155785 @default.
- W4293146040 hasConcept C86803240 @default.
- W4293146040 hasConcept C89600930 @default.
- W4293146040 hasConcept C94915269 @default.
- W4293146040 hasConceptScore W4293146040C115961682 @default.
- W4293146040 hasConceptScore W4293146040C11727466 @default.
- W4293146040 hasConceptScore W4293146040C146849305 @default.
- W4293146040 hasConceptScore W4293146040C151730666 @default.
- W4293146040 hasConceptScore W4293146040C154945302 @default.
- W4293146040 hasConceptScore W4293146040C177264268 @default.
- W4293146040 hasConceptScore W4293146040C184337299 @default.
- W4293146040 hasConceptScore W4293146040C199360897 @default.
- W4293146040 hasConceptScore W4293146040C2776760102 @default.
- W4293146040 hasConceptScore W4293146040C2779343474 @default.
- W4293146040 hasConceptScore W4293146040C2779803651 @default.
- W4293146040 hasConceptScore W4293146040C31972630 @default.
- W4293146040 hasConceptScore W4293146040C41008148 @default.
- W4293146040 hasConceptScore W4293146040C76155785 @default.
- W4293146040 hasConceptScore W4293146040C86803240 @default.
- W4293146040 hasConceptScore W4293146040C89600930 @default.
- W4293146040 hasConceptScore W4293146040C94915269 @default.
- W4293146040 hasFunder F4320306076 @default.
- W4293146040 hasFunder F4320321001 @default.
- W4293146040 hasLocation W42931460401 @default.
- W4293146040 hasOpenAccess W4293146040 @default.
- W4293146040 hasPrimaryLocation W42931460401 @default.
- W4293146040 hasRelatedWork W1574999717 @default.
- W4293146040 hasRelatedWork W166251047 @default.
- W4293146040 hasRelatedWork W2020564930 @default.
- W4293146040 hasRelatedWork W2059339452 @default.
- W4293146040 hasRelatedWork W2262668847 @default.
- W4293146040 hasRelatedWork W2370766994 @default.
- W4293146040 hasRelatedWork W2995115364 @default.
- W4293146040 hasRelatedWork W3195987654 @default.
- W4293146040 hasRelatedWork W3203509158 @default.
- W4293146040 hasRelatedWork W4214647905 @default.
- W4293146040 hasVolume "501" @default.
- W4293146040 isParatext "false" @default.
- W4293146040 isRetracted "false" @default.
- W4293146040 workType "article" @default.