Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894854504> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2894854504 endingPage "2512" @default.
- W2894854504 startingPage "2512" @default.
- W2894854504 abstract "Deep learning-based methods have reached state of the art performances, relying on a large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem, which consists of learning incrementally new classes and examples over time. Combining the outstanding performances of Deep Neural Networks (DNNs) with the flexibility of incremental learning techniques is a promising venue of research. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA is based on pre-trained DNNs as feature extractors, robust selection of feature vectors in subspaces using a nearest-class-mean based technique, majority votes and data augmentation at both the training and the prediction stages. Experiments on challenging vision datasets demonstrate the ability of the proposed method for low complexity incremental learning, while achieving significantly better accuracy than existing incremental counterparts." @default.
- W2894854504 created "2018-10-12" @default.
- W2894854504 creator A5025688483 @default.
- W2894854504 creator A5033923143 @default.
- W2894854504 creator A5043007083 @default.
- W2894854504 creator A5068330560 @default.
- W2894854504 creator A5073128964 @default.
- W2894854504 date "2018-12-06" @default.
- W2894854504 modified "2023-10-16" @default.
- W2894854504 title "Transfer Incremental Learning Using Data Augmentation" @default.
- W2894854504 cites W2015563892 @default.
- W2894854504 cites W2037307005 @default.
- W2894854504 cites W2052812103 @default.
- W2894854504 cites W2060277733 @default.
- W2894854504 cites W2103753221 @default.
- W2894854504 cites W2117539524 @default.
- W2894854504 cites W2161208102 @default.
- W2894854504 cites W2165698076 @default.
- W2894854504 doi "https://doi.org/10.3390/app8122512" @default.
- W2894854504 hasPublicationYear "2018" @default.
- W2894854504 type Work @default.
- W2894854504 sameAs 2894854504 @default.
- W2894854504 citedByCount "6" @default.
- W2894854504 countsByYear W28948545042019 @default.
- W2894854504 countsByYear W28948545042020 @default.
- W2894854504 countsByYear W28948545042021 @default.
- W2894854504 countsByYear W28948545042022 @default.
- W2894854504 crossrefType "journal-article" @default.
- W2894854504 hasAuthorship W2894854504A5025688483 @default.
- W2894854504 hasAuthorship W2894854504A5033923143 @default.
- W2894854504 hasAuthorship W2894854504A5043007083 @default.
- W2894854504 hasAuthorship W2894854504A5068330560 @default.
- W2894854504 hasAuthorship W2894854504A5073128964 @default.
- W2894854504 hasBestOaLocation W28948545041 @default.
- W2894854504 hasConcept C105795698 @default.
- W2894854504 hasConcept C108583219 @default.
- W2894854504 hasConcept C119857082 @default.
- W2894854504 hasConcept C148483581 @default.
- W2894854504 hasConcept C150899416 @default.
- W2894854504 hasConcept C154945302 @default.
- W2894854504 hasConcept C2777212361 @default.
- W2894854504 hasConcept C2780598303 @default.
- W2894854504 hasConcept C2780735816 @default.
- W2894854504 hasConcept C33923547 @default.
- W2894854504 hasConcept C41008148 @default.
- W2894854504 hasConceptScore W2894854504C105795698 @default.
- W2894854504 hasConceptScore W2894854504C108583219 @default.
- W2894854504 hasConceptScore W2894854504C119857082 @default.
- W2894854504 hasConceptScore W2894854504C148483581 @default.
- W2894854504 hasConceptScore W2894854504C150899416 @default.
- W2894854504 hasConceptScore W2894854504C154945302 @default.
- W2894854504 hasConceptScore W2894854504C2777212361 @default.
- W2894854504 hasConceptScore W2894854504C2780598303 @default.
- W2894854504 hasConceptScore W2894854504C2780735816 @default.
- W2894854504 hasConceptScore W2894854504C33923547 @default.
- W2894854504 hasConceptScore W2894854504C41008148 @default.
- W2894854504 hasIssue "12" @default.
- W2894854504 hasLocation W28948545041 @default.
- W2894854504 hasLocation W28948545042 @default.
- W2894854504 hasLocation W28948545043 @default.
- W2894854504 hasLocation W28948545044 @default.
- W2894854504 hasLocation W28948545045 @default.
- W2894854504 hasOpenAccess W2894854504 @default.
- W2894854504 hasPrimaryLocation W28948545041 @default.
- W2894854504 hasRelatedWork W2951211570 @default.
- W2894854504 hasRelatedWork W3023427754 @default.
- W2894854504 hasRelatedWork W3131673289 @default.
- W2894854504 hasRelatedWork W3167935049 @default.
- W2894854504 hasRelatedWork W3178390372 @default.
- W2894854504 hasRelatedWork W3192840557 @default.
- W2894854504 hasRelatedWork W3198847674 @default.
- W2894854504 hasRelatedWork W4206357785 @default.
- W2894854504 hasRelatedWork W4281381188 @default.
- W2894854504 hasRelatedWork W4375928479 @default.
- W2894854504 hasVolume "8" @default.
- W2894854504 isParatext "false" @default.
- W2894854504 isRetracted "false" @default.
- W2894854504 magId "2894854504" @default.
- W2894854504 workType "article" @default.