FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137470415> ?p ?o ?g. }

• W3137470415 abstract "In this paper, we study a not well-investigated but important transfer learning problem termed Distant Domain Transfer Learning (DDTL). This topic is closely related to negative transfer. Unlike conventional transfer learning problems which assume that the source domain and the target domain are more or less similar to each other, DDTL aims to make efficient transfers even when the domains or the tasks are completely different. As an extreme example in image classification, there are only a sufficient amount of unlabeled images of watches, airplanes, and horses in the source domain, and the target domain only has a small set of labeled human face images. Previously, a few instance-based distant domain transfer algorithms were proposed to deal with this type of binary distant domain image classification problems. Yet most existing algorithms are very task-specific and they are only good at binary classification tasks. In this study, we propose a novel feature-based distant domain transfer learning algorithm, which requires only a tiny set of labeled target data and unlabeled source data from completely different domains. Instead of selecting intermediate instances, we introduced Distant Feature Fusion (DFF), a novel feature selection method, to discover general features cross distant domains and tasks by using convolutional autoencoder with a domain distance measurement as a feature extractor. As the novelty of this study, it can effectively handle both distant domain mutil-class image classification and binary image classification problems. More importantly, it has achieved up to 19% higher classification accuracy than non-transfer algorithms, and up to 9% higher than existing distant transfer algorithms." @default.
• W3137470415 created "2021-03-29" @default.
• W3137470415 creator A5028748926 @default.
• W3137470415 creator A5032764121 @default.
• W3137470415 creator A5079301418 @default.
• W3137470415 creator A5079350189 @default.
• W3137470415 creator A5081717248 @default.
• W3137470415 date "2020-12-10" @default.
• W3137470415 modified "2023-09-24" @default.
• W3137470415 title "Feature-based Distant Domain Transfer Learning" @default.
• W3137470415 cites W1919803322 @default.
• W3137470415 cites W1985697265 @default.
• W3137470415 cites W2140494000 @default.
• W3137470415 cites W2164943005 @default.
• W3137470415 cites W2165698076 @default.
• W3137470415 cites W2253429366 @default.
• W3137470415 cites W2293066912 @default.
• W3137470415 cites W2577325523 @default.
• W3137470415 cites W2591924527 @default.
• W3137470415 cites W2592230399 @default.
• W3137470415 cites W2613274667 @default.
• W3137470415 cites W2945183595 @default.
• W3137470415 cites W2964288524 @default.
• W3137470415 cites W2964317695 @default.
• W3137470415 cites W3033901474 @default.
• W3137470415 cites W3085604187 @default.
• W3137470415 cites W3103998378 @default.
• W3137470415 cites W4255815195 @default.
• W3137470415 doi "https://doi.org/10.1109/bigdata50022.2020.9378493" @default.
• W3137470415 hasPublicationYear "2020" @default.
• W3137470415 type Work @default.
• W3137470415 sameAs 3137470415 @default.
• W3137470415 citedByCount "15" @default.
• W3137470415 countsByYear W31374704152020 @default.
• W3137470415 countsByYear W31374704152021 @default.
• W3137470415 countsByYear W31374704152022 @default.
• W3137470415 countsByYear W31374704152023 @default.
• W3137470415 crossrefType "proceedings-article" @default.
• W3137470415 hasAuthorship W3137470415A5028748926 @default.
• W3137470415 hasAuthorship W3137470415A5032764121 @default.
• W3137470415 hasAuthorship W3137470415A5079301418 @default.
• W3137470415 hasAuthorship W3137470415A5079350189 @default.
• W3137470415 hasAuthorship W3137470415A5081717248 @default.
• W3137470415 hasConcept C134306372 @default.
• W3137470415 hasConcept C138885662 @default.
• W3137470415 hasConcept C150899416 @default.
• W3137470415 hasConcept C153180895 @default.
• W3137470415 hasConcept C154945302 @default.
• W3137470415 hasConcept C2776401178 @default.
• W3137470415 hasConcept C33923547 @default.
• W3137470415 hasConcept C36503486 @default.
• W3137470415 hasConcept C41008148 @default.
• W3137470415 hasConcept C41895202 @default.
• W3137470415 hasConceptScore W3137470415C134306372 @default.
• W3137470415 hasConceptScore W3137470415C138885662 @default.
• W3137470415 hasConceptScore W3137470415C150899416 @default.
• W3137470415 hasConceptScore W3137470415C153180895 @default.
• W3137470415 hasConceptScore W3137470415C154945302 @default.
• W3137470415 hasConceptScore W3137470415C2776401178 @default.
• W3137470415 hasConceptScore W3137470415C33923547 @default.
• W3137470415 hasConceptScore W3137470415C36503486 @default.
• W3137470415 hasConceptScore W3137470415C41008148 @default.
• W3137470415 hasConceptScore W3137470415C41895202 @default.
• W3137470415 hasFunder F4320310348 @default.
• W3137470415 hasLocation W31374704151 @default.
• W3137470415 hasOpenAccess W3137470415 @default.
• W3137470415 hasPrimaryLocation W31374704151 @default.
• W3137470415 hasRelatedWork W2016461833 @default.
• W3137470415 hasRelatedWork W2052253960 @default.
• W3137470415 hasRelatedWork W2167955297 @default.
• W3137470415 hasRelatedWork W2382607599 @default.
• W3137470415 hasRelatedWork W2760085659 @default.
• W3137470415 hasRelatedWork W2970216048 @default.
• W3137470415 hasRelatedWork W2982233537 @default.
• W3137470415 hasRelatedWork W3197541072 @default.
• W3137470415 hasRelatedWork W376702462 @default.
• W3137470415 hasRelatedWork W4221167745 @default.
• W3137470415 isParatext "false" @default.
• W3137470415 isRetracted "false" @default.
• W3137470415 magId "3137470415" @default.
• W3137470415 workType "article" @default.