FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805111009> ?p ?o ?g. }

• W2805111009 endingPage "852" @default.
• W2805111009 startingPage "845" @default.
• W2805111009 abstract "Abstract. In this paper we deal with the problem of measuring the similarity between training and tests datasets in the context of transfer learning (TL) for image classification. TL tries to transfer knowledge from a source domain, where labelled training samples are abundant but the data may follow a different distribution, to a target domain, where labelled training samples are scarce or even unavailable, assuming that the domains are related. Thus, the requirements w.r.t. the availability of labelled training samples in the target domain are reduced. In particular, if no labelled target data are available, it is inherently difficult to find a robust measure of relatedness between the source and target domains. This is of crucial importance for the performance of TL, because the knowledge transfer between unrelated data may lead to negative transfer, i.e. to a decrease of classification performance after transfer. We address the problem of measuring the relatedness between source and target datasets and investigate three different strategies to predict and, consequently, to avoid negative transfer in this paper. The first strategy is based on circular validation. The second strategy relies on the Maximum Mean Discrepancy (MMD) similarity metric, whereas the third one is an extension of MMD which incorporates the knowledge about the class labels in the source domain. Our method is evaluated using two different benchmark datasets. The experiments highlight the strengths and weaknesses of the investigated methods. We also show that it is possible to reduce the amount of negative transfer using these strategies for a TL method and to generate a consistent performance improvement over the whole dataset." @default.
• W2805111009 created "2018-06-13" @default.
• W2805111009 creator A5000403411 @default.
• W2805111009 creator A5033807047 @default.
• W2805111009 creator A5064913233 @default.
• W2805111009 creator A5069418475 @default.
• W2805111009 creator A5072465522 @default.
• W2805111009 date "2018-05-30" @default.
• W2805111009 modified "2023-10-18" @default.
• W2805111009 title "A COMPARISON OF TWO STRATEGIES FOR AVOIDING NEGATIVE TRANSFER IN DOMAIN ADAPTATION BASED ON LOGISTIC REGRESSION" @default.
• W2805111009 cites W1663973292 @default.
• W2805111009 cites W1919803322 @default.
• W2805111009 cites W2075728230 @default.
• W2805111009 cites W2081621443 @default.
• W2805111009 cites W2098027503 @default.
• W2805111009 cites W2159570078 @default.
• W2805111009 cites W2165698076 @default.
• W2805111009 cites W2212660284 @default.
• W2805111009 cites W2212983101 @default.
• W2805111009 cites W2311217941 @default.
• W2805111009 cites W2756073160 @default.
• W2805111009 cites W2911964244 @default.
• W2805111009 cites W3035219538 @default.
• W2805111009 doi "https://doi.org/10.5194/isprs-archives-xlii-2-845-2018" @default.
• W2805111009 hasPublicationYear "2018" @default.
• W2805111009 type Work @default.
• W2805111009 sameAs 2805111009 @default.
• W2805111009 citedByCount "3" @default.
• W2805111009 countsByYear W28051110092019 @default.
• W2805111009 countsByYear W28051110092021 @default.
• W2805111009 countsByYear W28051110092022 @default.
• W2805111009 crossrefType "journal-article" @default.
• W2805111009 hasAuthorship W2805111009A5000403411 @default.
• W2805111009 hasAuthorship W2805111009A5033807047 @default.
• W2805111009 hasAuthorship W2805111009A5064913233 @default.
• W2805111009 hasAuthorship W2805111009A5069418475 @default.
• W2805111009 hasAuthorship W2805111009A5072465522 @default.
• W2805111009 hasBestOaLocation W28051110091 @default.
• W2805111009 hasConcept C103278499 @default.
• W2805111009 hasConcept C115961682 @default.
• W2805111009 hasConcept C119857082 @default.
• W2805111009 hasConcept C124101348 @default.
• W2805111009 hasConcept C13280743 @default.
• W2805111009 hasConcept C134306372 @default.
• W2805111009 hasConcept C138885662 @default.
• W2805111009 hasConcept C150899416 @default.
• W2805111009 hasConcept C151730666 @default.
• W2805111009 hasConcept C153180895 @default.
• W2805111009 hasConcept C154945302 @default.
• W2805111009 hasConcept C162324750 @default.
• W2805111009 hasConcept C171041071 @default.
• W2805111009 hasConcept C173608175 @default.
• W2805111009 hasConcept C176217482 @default.
• W2805111009 hasConcept C185798385 @default.
• W2805111009 hasConcept C205649164 @default.
• W2805111009 hasConcept C21547014 @default.
• W2805111009 hasConcept C2776175482 @default.
• W2805111009 hasConcept C2776434776 @default.
• W2805111009 hasConcept C2776960227 @default.
• W2805111009 hasConcept C2779178101 @default.
• W2805111009 hasConcept C2779343474 @default.
• W2805111009 hasConcept C2780009758 @default.
• W2805111009 hasConcept C33923547 @default.
• W2805111009 hasConcept C36503486 @default.
• W2805111009 hasConcept C41008148 @default.
• W2805111009 hasConcept C41895202 @default.
• W2805111009 hasConcept C56739046 @default.
• W2805111009 hasConcept C86803240 @default.
• W2805111009 hasConcept C95623464 @default.
• W2805111009 hasConceptScore W2805111009C103278499 @default.
• W2805111009 hasConceptScore W2805111009C115961682 @default.
• W2805111009 hasConceptScore W2805111009C119857082 @default.
• W2805111009 hasConceptScore W2805111009C124101348 @default.
• W2805111009 hasConceptScore W2805111009C13280743 @default.
• W2805111009 hasConceptScore W2805111009C134306372 @default.
• W2805111009 hasConceptScore W2805111009C138885662 @default.
• W2805111009 hasConceptScore W2805111009C150899416 @default.
• W2805111009 hasConceptScore W2805111009C151730666 @default.
• W2805111009 hasConceptScore W2805111009C153180895 @default.
• W2805111009 hasConceptScore W2805111009C154945302 @default.
• W2805111009 hasConceptScore W2805111009C162324750 @default.
• W2805111009 hasConceptScore W2805111009C171041071 @default.
• W2805111009 hasConceptScore W2805111009C173608175 @default.
• W2805111009 hasConceptScore W2805111009C176217482 @default.
• W2805111009 hasConceptScore W2805111009C185798385 @default.
• W2805111009 hasConceptScore W2805111009C205649164 @default.
• W2805111009 hasConceptScore W2805111009C21547014 @default.
• W2805111009 hasConceptScore W2805111009C2776175482 @default.
• W2805111009 hasConceptScore W2805111009C2776434776 @default.
• W2805111009 hasConceptScore W2805111009C2776960227 @default.
• W2805111009 hasConceptScore W2805111009C2779178101 @default.
• W2805111009 hasConceptScore W2805111009C2779343474 @default.
• W2805111009 hasConceptScore W2805111009C2780009758 @default.
• W2805111009 hasConceptScore W2805111009C33923547 @default.
• W2805111009 hasConceptScore W2805111009C36503486 @default.
• W2805111009 hasConceptScore W2805111009C41008148 @default.
• W2805111009 hasConceptScore W2805111009C41895202 @default.
• W2805111009 hasConceptScore W2805111009C56739046 @default.

• next