Matches in SemOpenAlex for { <https://semopenalex.org/work/W331395217> ?p ?o ?g. }
- W331395217 endingPage "300" @default.
- W331395217 startingPage "290" @default.
- W331395217 abstract "In this work we explore the idea that, in the presence of a small training set of images, it could be beneficial to use that set itself to obtain a transformed training set (by performing a random rotation on each sample), train a source network using the transformed data, then retrain the source network using the original data. Applying this transfer learning technique to three different types of character data, we achieve average relative improvements between 6 % and 16 % in the classification test error. Furthermore, we show that it is possible to achieve relative improvements between 8 % and 42 % in cases where the amount of original training samples is very limited (30 samples per class), by introducing not just one rotation but several random rotations per sample." @default.
- W331395217 created "2016-06-24" @default.
- W331395217 creator A5009791474 @default.
- W331395217 creator A5012244391 @default.
- W331395217 creator A5068291255 @default.
- W331395217 creator A5079688385 @default.
- W331395217 creator A5081631078 @default.
- W331395217 creator A5086534417 @default.
- W331395217 date "2014-01-01" @default.
- W331395217 modified "2023-10-17" @default.
- W331395217 title "Transfer Learning Using Rotated Image Data to Improve Deep Neural Network Performance" @default.
- W331395217 cites W1994197834 @default.
- W331395217 cites W1998582365 @default.
- W331395217 cites W2132424367 @default.
- W331395217 cites W2136922672 @default.
- W331395217 cites W2163922914 @default.
- W331395217 cites W2165698076 @default.
- W331395217 cites W4231109964 @default.
- W331395217 doi "https://doi.org/10.1007/978-3-319-11758-4_32" @default.
- W331395217 hasPublicationYear "2014" @default.
- W331395217 type Work @default.
- W331395217 sameAs 331395217 @default.
- W331395217 citedByCount "8" @default.
- W331395217 countsByYear W3313952172016 @default.
- W331395217 countsByYear W3313952172017 @default.
- W331395217 countsByYear W3313952172018 @default.
- W331395217 countsByYear W3313952172019 @default.
- W331395217 countsByYear W3313952172020 @default.
- W331395217 countsByYear W3313952172023 @default.
- W331395217 crossrefType "book-chapter" @default.
- W331395217 hasAuthorship W331395217A5009791474 @default.
- W331395217 hasAuthorship W331395217A5012244391 @default.
- W331395217 hasAuthorship W331395217A5068291255 @default.
- W331395217 hasAuthorship W331395217A5079688385 @default.
- W331395217 hasAuthorship W331395217A5081631078 @default.
- W331395217 hasAuthorship W331395217A5086534417 @default.
- W331395217 hasBestOaLocation W3313952172 @default.
- W331395217 hasConcept C115961682 @default.
- W331395217 hasConcept C119857082 @default.
- W331395217 hasConcept C138885662 @default.
- W331395217 hasConcept C150899416 @default.
- W331395217 hasConcept C153180895 @default.
- W331395217 hasConcept C154945302 @default.
- W331395217 hasConcept C16910744 @default.
- W331395217 hasConcept C169903167 @default.
- W331395217 hasConcept C171041071 @default.
- W331395217 hasConcept C173608175 @default.
- W331395217 hasConcept C177264268 @default.
- W331395217 hasConcept C185592680 @default.
- W331395217 hasConcept C198531522 @default.
- W331395217 hasConcept C199360897 @default.
- W331395217 hasConcept C2524010 @default.
- W331395217 hasConcept C2776175482 @default.
- W331395217 hasConcept C2777212361 @default.
- W331395217 hasConcept C2779178101 @default.
- W331395217 hasConcept C2780861071 @default.
- W331395217 hasConcept C33923547 @default.
- W331395217 hasConcept C41008148 @default.
- W331395217 hasConcept C41895202 @default.
- W331395217 hasConcept C43617362 @default.
- W331395217 hasConcept C50644808 @default.
- W331395217 hasConcept C51632099 @default.
- W331395217 hasConcept C58489278 @default.
- W331395217 hasConcept C74050887 @default.
- W331395217 hasConceptScore W331395217C115961682 @default.
- W331395217 hasConceptScore W331395217C119857082 @default.
- W331395217 hasConceptScore W331395217C138885662 @default.
- W331395217 hasConceptScore W331395217C150899416 @default.
- W331395217 hasConceptScore W331395217C153180895 @default.
- W331395217 hasConceptScore W331395217C154945302 @default.
- W331395217 hasConceptScore W331395217C16910744 @default.
- W331395217 hasConceptScore W331395217C169903167 @default.
- W331395217 hasConceptScore W331395217C171041071 @default.
- W331395217 hasConceptScore W331395217C173608175 @default.
- W331395217 hasConceptScore W331395217C177264268 @default.
- W331395217 hasConceptScore W331395217C185592680 @default.
- W331395217 hasConceptScore W331395217C198531522 @default.
- W331395217 hasConceptScore W331395217C199360897 @default.
- W331395217 hasConceptScore W331395217C2524010 @default.
- W331395217 hasConceptScore W331395217C2776175482 @default.
- W331395217 hasConceptScore W331395217C2777212361 @default.
- W331395217 hasConceptScore W331395217C2779178101 @default.
- W331395217 hasConceptScore W331395217C2780861071 @default.
- W331395217 hasConceptScore W331395217C33923547 @default.
- W331395217 hasConceptScore W331395217C41008148 @default.
- W331395217 hasConceptScore W331395217C41895202 @default.
- W331395217 hasConceptScore W331395217C43617362 @default.
- W331395217 hasConceptScore W331395217C50644808 @default.
- W331395217 hasConceptScore W331395217C51632099 @default.
- W331395217 hasConceptScore W331395217C58489278 @default.
- W331395217 hasConceptScore W331395217C74050887 @default.
- W331395217 hasLocation W3313952171 @default.
- W331395217 hasLocation W3313952172 @default.
- W331395217 hasOpenAccess W331395217 @default.
- W331395217 hasPrimaryLocation W3313952171 @default.
- W331395217 hasRelatedWork W2012689841 @default.
- W331395217 hasRelatedWork W2071508803 @default.
- W331395217 hasRelatedWork W2123376283 @default.