FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950349738> ?p ?o ?g. }

• W2950349738 abstract "How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context of image classification. We frame this quest as an active learning problem and use zero-shot classifiers to guide the learning process by linking the new task to the existing classifiers. By revisiting the dual formulation of adaptive SVM, we reveal two basic conditions to choose greedily only the most relevant samples to be annotated. On this basis we propose an effective active learning algorithm which learns the best possible target classification model with minimum human labeling effort. Extensive experiments on two challenging datasets show the value of our approach compared to the state-of-the-art active learning methodologies, as well as its potential to reuse past datasets with minimal effort for future tasks." @default.
• W2950349738 created "2019-06-27" @default.
• W2950349738 creator A5002625178 @default.
• W2950349738 creator A5004857169 @default.
• W2950349738 creator A5024508073 @default.
• W2950349738 creator A5056112540 @default.
• W2950349738 creator A5074816094 @default.
• W2950349738 date "2015-10-06" @default.
• W2950349738 modified "2023-10-17" @default.
• W2950349738 title "Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks" @default.
• W2950349738 cites W129091472 @default.
• W2950349738 cites W1514940655 @default.
• W2950349738 cites W1964763677 @default.
• W2950349738 cites W1982522767 @default.
• W2950349738 cites W1983521647 @default.
• W2950349738 cites W1992454046 @default.
• W2950349738 cites W1995713768 @default.
• W2950349738 cites W2013044826 @default.
• W2950349738 cites W2027248184 @default.
• W2950349738 cites W2027953712 @default.
• W2950349738 cites W2042932437 @default.
• W2950349738 cites W2078846315 @default.
• W2950349738 cites W2086686352 @default.
• W2950349738 cites W2108598243 @default.
• W2950349738 cites W2120354757 @default.
• W2950349738 cites W2123024445 @default.
• W2950349738 cites W2125094180 @default.
• W2950349738 cites W2127816222 @default.
• W2950349738 cites W2139185560 @default.
• W2950349738 cites W2145276819 @default.
• W2950349738 cites W2149676790 @default.
• W2950349738 cites W2159570078 @default.
• W2950349738 cites W2165698076 @default.
• W2950349738 cites W2262342046 @default.
• W2950349738 cites W2426031434 @default.
• W2950349738 cites W2903158431 @default.
• W2950349738 cites W2950276680 @default.
• W2950349738 cites W2950700180 @default.
• W2950349738 hasPublicationYear "2015" @default.
• W2950349738 type Work @default.
• W2950349738 sameAs 2950349738 @default.
• W2950349738 citedByCount "6" @default.
• W2950349738 countsByYear W29503497382016 @default.
• W2950349738 countsByYear W29503497382017 @default.
• W2950349738 countsByYear W29503497382018 @default.
• W2950349738 crossrefType "posted-content" @default.
• W2950349738 hasAuthorship W2950349738A5002625178 @default.
• W2950349738 hasAuthorship W2950349738A5004857169 @default.
• W2950349738 hasAuthorship W2950349738A5024508073 @default.
• W2950349738 hasAuthorship W2950349738A5056112540 @default.
• W2950349738 hasAuthorship W2950349738A5074816094 @default.
• W2950349738 hasConcept C107673813 @default.
• W2950349738 hasConcept C111919701 @default.
• W2950349738 hasConcept C119857082 @default.
• W2950349738 hasConcept C12267149 @default.
• W2950349738 hasConcept C126042441 @default.
• W2950349738 hasConcept C150899416 @default.
• W2950349738 hasConcept C151730666 @default.
• W2950349738 hasConcept C154945302 @default.
• W2950349738 hasConcept C162324750 @default.
• W2950349738 hasConcept C177264268 @default.
• W2950349738 hasConcept C177769412 @default.
• W2950349738 hasConcept C187736073 @default.
• W2950349738 hasConcept C18903297 @default.
• W2950349738 hasConcept C199360897 @default.
• W2950349738 hasConcept C206588197 @default.
• W2950349738 hasConcept C2779343474 @default.
• W2950349738 hasConcept C2780451532 @default.
• W2950349738 hasConcept C41008148 @default.
• W2950349738 hasConcept C76155785 @default.
• W2950349738 hasConcept C77967617 @default.
• W2950349738 hasConcept C86803240 @default.
• W2950349738 hasConcept C98045186 @default.
• W2950349738 hasConceptScore W2950349738C107673813 @default.
• W2950349738 hasConceptScore W2950349738C111919701 @default.
• W2950349738 hasConceptScore W2950349738C119857082 @default.
• W2950349738 hasConceptScore W2950349738C12267149 @default.
• W2950349738 hasConceptScore W2950349738C126042441 @default.
• W2950349738 hasConceptScore W2950349738C150899416 @default.
• W2950349738 hasConceptScore W2950349738C151730666 @default.
• W2950349738 hasConceptScore W2950349738C154945302 @default.
• W2950349738 hasConceptScore W2950349738C162324750 @default.
• W2950349738 hasConceptScore W2950349738C177264268 @default.
• W2950349738 hasConceptScore W2950349738C177769412 @default.
• W2950349738 hasConceptScore W2950349738C187736073 @default.
• W2950349738 hasConceptScore W2950349738C18903297 @default.
• W2950349738 hasConceptScore W2950349738C199360897 @default.
• W2950349738 hasConceptScore W2950349738C206588197 @default.
• W2950349738 hasConceptScore W2950349738C2779343474 @default.
• W2950349738 hasConceptScore W2950349738C2780451532 @default.
• W2950349738 hasConceptScore W2950349738C41008148 @default.
• W2950349738 hasConceptScore W2950349738C76155785 @default.
• W2950349738 hasConceptScore W2950349738C77967617 @default.
• W2950349738 hasConceptScore W2950349738C86803240 @default.
• W2950349738 hasConceptScore W2950349738C98045186 @default.
• W2950349738 hasOpenAccess W2950349738 @default.
• W2950349738 hasRelatedWork W2043254690 @default.
• W2950349738 hasRelatedWork W2073683004 @default.
• W2950349738 hasRelatedWork W2107213321 @default.
• W2950349738 hasRelatedWork W2108598243 @default.

• next