Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034335103> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3034335103 abstract "Unsupervised domain adaptation (UDA) casts a light when dealing with insufficient or no labeled data in the target domain by exploring the well-annotated source knowledge in different distributions. Most research efforts on UDA explore to seek a domain-invariant classifier over source supervision. However, due to the scarcity of label information in the target domain, such a classifier has a lack of ground-truth target supervision, which dramatically obstructs the robustness and discrimination of the classifier. To this end, we develop a novel Generative cross-domain learning via Structure-Preserving (GSP), which attempts to transform target data into the source domain in order to take advantage of source supervision. Specifically, a novel cross-domain graph alignment is developed to capture the intrinsic relationship across two domains during target-source translation. Simultaneously, two distinct classifiers are trained to trigger the domain-invariant feature learning both guided with source supervision, one is a traditional source classifier and the other is a source-supervised target classifier. Extensive experimental results on several cross-domain visual benchmarks have demonstrated the effectiveness of our model by comparing with other state-of-the-art UDA algorithms." @default.
- W3034335103 created "2020-06-19" @default.
- W3034335103 creator A5051051967 @default.
- W3034335103 creator A5083458247 @default.
- W3034335103 date "2020-06-01" @default.
- W3034335103 modified "2023-09-23" @default.
- W3034335103 title "Structure Preserving Generative Cross-Domain Learning" @default.
- W3034335103 cites W1923184257 @default.
- W3034335103 cites W1982465050 @default.
- W3034335103 cites W2108598243 @default.
- W3034335103 cites W2194775991 @default.
- W3034335103 cites W2593768305 @default.
- W3034335103 cites W2627183927 @default.
- W3034335103 cites W2739759330 @default.
- W3034335103 cites W2798681837 @default.
- W3034335103 cites W2904706552 @default.
- W3034335103 cites W2913699508 @default.
- W3034335103 cites W2962687275 @default.
- W3034335103 cites W2963073217 @default.
- W3034335103 cites W2963532621 @default.
- W3034335103 cites W2963858297 @default.
- W3034335103 cites W2963993484 @default.
- W3034335103 cites W2964285681 @default.
- W3034335103 cites W2965954137 @default.
- W3034335103 cites W2966145398 @default.
- W3034335103 cites W2969893028 @default.
- W3034335103 cites W2979920800 @default.
- W3034335103 cites W2980096013 @default.
- W3034335103 cites W2981630749 @default.
- W3034335103 cites W2981720610 @default.
- W3034335103 cites W2982204955 @default.
- W3034335103 cites W2982259084 @default.
- W3034335103 cites W2998459790 @default.
- W3034335103 cites W3000097396 @default.
- W3034335103 cites W3035260401 @default.
- W3034335103 doi "https://doi.org/10.1109/cvpr42600.2020.00442" @default.
- W3034335103 hasPublicationYear "2020" @default.
- W3034335103 type Work @default.
- W3034335103 sameAs 3034335103 @default.
- W3034335103 citedByCount "32" @default.
- W3034335103 countsByYear W30343351032019 @default.
- W3034335103 countsByYear W30343351032020 @default.
- W3034335103 countsByYear W30343351032021 @default.
- W3034335103 countsByYear W30343351032022 @default.
- W3034335103 countsByYear W30343351032023 @default.
- W3034335103 crossrefType "proceedings-article" @default.
- W3034335103 hasAuthorship W3034335103A5051051967 @default.
- W3034335103 hasAuthorship W3034335103A5083458247 @default.
- W3034335103 hasConcept C119857082 @default.
- W3034335103 hasConcept C153180895 @default.
- W3034335103 hasConcept C154945302 @default.
- W3034335103 hasConcept C2776145971 @default.
- W3034335103 hasConcept C2776434776 @default.
- W3034335103 hasConcept C39890363 @default.
- W3034335103 hasConcept C41008148 @default.
- W3034335103 hasConcept C95623464 @default.
- W3034335103 hasConceptScore W3034335103C119857082 @default.
- W3034335103 hasConceptScore W3034335103C153180895 @default.
- W3034335103 hasConceptScore W3034335103C154945302 @default.
- W3034335103 hasConceptScore W3034335103C2776145971 @default.
- W3034335103 hasConceptScore W3034335103C2776434776 @default.
- W3034335103 hasConceptScore W3034335103C39890363 @default.
- W3034335103 hasConceptScore W3034335103C41008148 @default.
- W3034335103 hasConceptScore W3034335103C95623464 @default.
- W3034335103 hasLocation W30343351031 @default.
- W3034335103 hasOpenAccess W3034335103 @default.
- W3034335103 hasPrimaryLocation W30343351031 @default.
- W3034335103 hasRelatedWork W11223206 @default.
- W3034335103 hasRelatedWork W11705192 @default.
- W3034335103 hasRelatedWork W1361726 @default.
- W3034335103 hasRelatedWork W14047543 @default.
- W3034335103 hasRelatedWork W351505 @default.
- W3034335103 hasRelatedWork W3891032 @default.
- W3034335103 hasRelatedWork W4615079 @default.
- W3034335103 hasRelatedWork W6191748 @default.
- W3034335103 hasRelatedWork W8015944 @default.
- W3034335103 hasRelatedWork W9190101 @default.
- W3034335103 isParatext "false" @default.
- W3034335103 isRetracted "false" @default.
- W3034335103 magId "3034335103" @default.
- W3034335103 workType "article" @default.