Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963696518> ?p ?o ?g. }
- W2963696518 abstract "Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like semantic segmentation. Recent works have proposed to rely on synthetically generated imagery to ease the training set creation. However, models trained on these kind of data usually under-perform on real images due to the well known issue of domain shift. We address this problem by learning a domain-to-domain image translation GAN to shrink the gap between real and synthetic images. Peculiarly to our method, we introduce semantic constraints into the generation process to both avoid artifacts and guide the synthesis. To prove the effectiveness of our proposal, we show how a semantic segmentation CNN trained on images from the synthetic GTA dataset adapted by our method can improve performance by more than 16% mIoU with respect to the same model trained on synthetic images." @default.
- W2963696518 created "2019-07-30" @default.
- W2963696518 creator A5017431855 @default.
- W2963696518 creator A5025618347 @default.
- W2963696518 creator A5054437049 @default.
- W2963696518 date "2018-12-01" @default.
- W2963696518 modified "2023-10-16" @default.
- W2963696518 title "Exploiting semantics in adversarial training for image-level domain adaptation" @default.
- W2963696518 cites W1903029394 @default.
- W2963696518 cites W1905829557 @default.
- W2963696518 cites W1982696459 @default.
- W2963696518 cites W2116496396 @default.
- W2963696518 cites W2124592697 @default.
- W2963696518 cites W2128053425 @default.
- W2963696518 cites W2149466042 @default.
- W2963696518 cites W2340897893 @default.
- W2963696518 cites W2412782625 @default.
- W2963696518 cites W2431874326 @default.
- W2963696518 cites W2487365028 @default.
- W2963696518 cites W2560023338 @default.
- W2963696518 cites W2593768305 @default.
- W2963696518 cites W2739759330 @default.
- W2963696518 cites W2756073160 @default.
- W2963696518 cites W2786808285 @default.
- W2963696518 cites W2962793481 @default.
- W2963696518 cites W2962891704 @default.
- W2963696518 cites W2962899390 @default.
- W2963696518 cites W2963073614 @default.
- W2963696518 cites W2963709863 @default.
- W2963696518 cites W2963881378 @default.
- W2963696518 cites W2964047820 @default.
- W2963696518 cites W2964309882 @default.
- W2963696518 doi "https://doi.org/10.1109/ipas.2018.8708884" @default.
- W2963696518 hasPublicationYear "2018" @default.
- W2963696518 type Work @default.
- W2963696518 sameAs 2963696518 @default.
- W2963696518 citedByCount "27" @default.
- W2963696518 countsByYear W29636965182019 @default.
- W2963696518 countsByYear W29636965182020 @default.
- W2963696518 countsByYear W29636965182021 @default.
- W2963696518 countsByYear W29636965182022 @default.
- W2963696518 countsByYear W29636965182023 @default.
- W2963696518 crossrefType "proceedings-article" @default.
- W2963696518 hasAuthorship W2963696518A5017431855 @default.
- W2963696518 hasAuthorship W2963696518A5025618347 @default.
- W2963696518 hasAuthorship W2963696518A5054437049 @default.
- W2963696518 hasBestOaLocation W29636965182 @default.
- W2963696518 hasConcept C108583219 @default.
- W2963696518 hasConcept C111919701 @default.
- W2963696518 hasConcept C115961682 @default.
- W2963696518 hasConcept C119857082 @default.
- W2963696518 hasConcept C120665830 @default.
- W2963696518 hasConcept C121332964 @default.
- W2963696518 hasConcept C124504099 @default.
- W2963696518 hasConcept C134306372 @default.
- W2963696518 hasConcept C139807058 @default.
- W2963696518 hasConcept C154945302 @default.
- W2963696518 hasConcept C160920958 @default.
- W2963696518 hasConcept C177264268 @default.
- W2963696518 hasConcept C184337299 @default.
- W2963696518 hasConcept C199360897 @default.
- W2963696518 hasConcept C2776321320 @default.
- W2963696518 hasConcept C2776434776 @default.
- W2963696518 hasConcept C2779757391 @default.
- W2963696518 hasConcept C33923547 @default.
- W2963696518 hasConcept C36503486 @default.
- W2963696518 hasConcept C37736160 @default.
- W2963696518 hasConcept C41008148 @default.
- W2963696518 hasConcept C51632099 @default.
- W2963696518 hasConcept C89600930 @default.
- W2963696518 hasConcept C95623464 @default.
- W2963696518 hasConcept C98045186 @default.
- W2963696518 hasConceptScore W2963696518C108583219 @default.
- W2963696518 hasConceptScore W2963696518C111919701 @default.
- W2963696518 hasConceptScore W2963696518C115961682 @default.
- W2963696518 hasConceptScore W2963696518C119857082 @default.
- W2963696518 hasConceptScore W2963696518C120665830 @default.
- W2963696518 hasConceptScore W2963696518C121332964 @default.
- W2963696518 hasConceptScore W2963696518C124504099 @default.
- W2963696518 hasConceptScore W2963696518C134306372 @default.
- W2963696518 hasConceptScore W2963696518C139807058 @default.
- W2963696518 hasConceptScore W2963696518C154945302 @default.
- W2963696518 hasConceptScore W2963696518C160920958 @default.
- W2963696518 hasConceptScore W2963696518C177264268 @default.
- W2963696518 hasConceptScore W2963696518C184337299 @default.
- W2963696518 hasConceptScore W2963696518C199360897 @default.
- W2963696518 hasConceptScore W2963696518C2776321320 @default.
- W2963696518 hasConceptScore W2963696518C2776434776 @default.
- W2963696518 hasConceptScore W2963696518C2779757391 @default.
- W2963696518 hasConceptScore W2963696518C33923547 @default.
- W2963696518 hasConceptScore W2963696518C36503486 @default.
- W2963696518 hasConceptScore W2963696518C37736160 @default.
- W2963696518 hasConceptScore W2963696518C41008148 @default.
- W2963696518 hasConceptScore W2963696518C51632099 @default.
- W2963696518 hasConceptScore W2963696518C89600930 @default.
- W2963696518 hasConceptScore W2963696518C95623464 @default.
- W2963696518 hasConceptScore W2963696518C98045186 @default.
- W2963696518 hasLocation W29636965181 @default.
- W2963696518 hasLocation W29636965182 @default.
- W2963696518 hasOpenAccess W2963696518 @default.