Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211126960> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3211126960 endingPage "108384" @default.
- W3211126960 startingPage "108384" @default.
- W3211126960 abstract "Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions at a global image level but neglect the inconsistency around local image regions. This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. MLAN has two novel designs, namely, region-level adversarial learning (RL-AL) and co-regularized adversarial learning (CR-AL). Specifically, RL-AL models prototypical regional context-relations explicitly in the feature space of a labelled source domain and transfers them to an unlabelled target domain via adversarial learning. CR-AL fuses region-level AL and image-level AL optimally via mutual regularization. In addition, we design a multi-level consistency map that can guide domain adaptation in both input space (i.e., image-to-image translation) and output space (i.e., self-training) effectively. Extensive experiments show that MLAN outperforms the state-of-the-art with a large margin consistently across multiple datasets." @default.
- W3211126960 created "2021-11-08" @default.
- W3211126960 creator A5023507910 @default.
- W3211126960 creator A5067989804 @default.
- W3211126960 creator A5071429662 @default.
- W3211126960 creator A5079132449 @default.
- W3211126960 date "2022-03-01" @default.
- W3211126960 modified "2023-09-26" @default.
- W3211126960 title "Multi-level adversarial network for domain adaptive semantic segmentation" @default.
- W3211126960 cites W2412782625 @default.
- W3211126960 cites W2740924709 @default.
- W3211126960 cites W2762468750 @default.
- W3211126960 cites W2793888044 @default.
- W3211126960 cites W2965604235 @default.
- W3211126960 cites W2991162376 @default.
- W3211126960 cites W3039489616 @default.
- W3211126960 cites W3110778272 @default.
- W3211126960 cites W3134134173 @default.
- W3211126960 doi "https://doi.org/10.1016/j.patcog.2021.108384" @default.
- W3211126960 hasPublicationYear "2022" @default.
- W3211126960 type Work @default.
- W3211126960 sameAs 3211126960 @default.
- W3211126960 citedByCount "14" @default.
- W3211126960 countsByYear W32111269602021 @default.
- W3211126960 countsByYear W32111269602022 @default.
- W3211126960 countsByYear W32111269602023 @default.
- W3211126960 crossrefType "journal-article" @default.
- W3211126960 hasAuthorship W3211126960A5023507910 @default.
- W3211126960 hasAuthorship W3211126960A5067989804 @default.
- W3211126960 hasAuthorship W3211126960A5071429662 @default.
- W3211126960 hasAuthorship W3211126960A5079132449 @default.
- W3211126960 hasConcept C115961682 @default.
- W3211126960 hasConcept C119857082 @default.
- W3211126960 hasConcept C134306372 @default.
- W3211126960 hasConcept C153180895 @default.
- W3211126960 hasConcept C154945302 @default.
- W3211126960 hasConcept C166957645 @default.
- W3211126960 hasConcept C205649164 @default.
- W3211126960 hasConcept C2776135515 @default.
- W3211126960 hasConcept C2776434776 @default.
- W3211126960 hasConcept C2776436953 @default.
- W3211126960 hasConcept C2779343474 @default.
- W3211126960 hasConcept C2779757391 @default.
- W3211126960 hasConcept C33923547 @default.
- W3211126960 hasConcept C36503486 @default.
- W3211126960 hasConcept C37736160 @default.
- W3211126960 hasConcept C41008148 @default.
- W3211126960 hasConcept C774472 @default.
- W3211126960 hasConcept C89600930 @default.
- W3211126960 hasConcept C95623464 @default.
- W3211126960 hasConceptScore W3211126960C115961682 @default.
- W3211126960 hasConceptScore W3211126960C119857082 @default.
- W3211126960 hasConceptScore W3211126960C134306372 @default.
- W3211126960 hasConceptScore W3211126960C153180895 @default.
- W3211126960 hasConceptScore W3211126960C154945302 @default.
- W3211126960 hasConceptScore W3211126960C166957645 @default.
- W3211126960 hasConceptScore W3211126960C205649164 @default.
- W3211126960 hasConceptScore W3211126960C2776135515 @default.
- W3211126960 hasConceptScore W3211126960C2776434776 @default.
- W3211126960 hasConceptScore W3211126960C2776436953 @default.
- W3211126960 hasConceptScore W3211126960C2779343474 @default.
- W3211126960 hasConceptScore W3211126960C2779757391 @default.
- W3211126960 hasConceptScore W3211126960C33923547 @default.
- W3211126960 hasConceptScore W3211126960C36503486 @default.
- W3211126960 hasConceptScore W3211126960C37736160 @default.
- W3211126960 hasConceptScore W3211126960C41008148 @default.
- W3211126960 hasConceptScore W3211126960C774472 @default.
- W3211126960 hasConceptScore W3211126960C89600930 @default.
- W3211126960 hasConceptScore W3211126960C95623464 @default.
- W3211126960 hasFunder F4320327962 @default.
- W3211126960 hasLocation W32111269601 @default.
- W3211126960 hasOpenAccess W3211126960 @default.
- W3211126960 hasPrimaryLocation W32111269601 @default.
- W3211126960 hasRelatedWork W2990774877 @default.
- W3211126960 hasRelatedWork W2991081409 @default.
- W3211126960 hasRelatedWork W2995469692 @default.
- W3211126960 hasRelatedWork W3004969510 @default.
- W3211126960 hasRelatedWork W3043289511 @default.
- W3211126960 hasRelatedWork W3046843850 @default.
- W3211126960 hasRelatedWork W3138532924 @default.
- W3211126960 hasRelatedWork W3174713482 @default.
- W3211126960 hasRelatedWork W4312525628 @default.
- W3211126960 hasRelatedWork W4382541548 @default.
- W3211126960 hasVolume "123" @default.
- W3211126960 isParatext "false" @default.
- W3211126960 isRetracted "false" @default.
- W3211126960 magId "3211126960" @default.
- W3211126960 workType "article" @default.