Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554170757> ?p ?o ?g. }
- W2554170757 endingPage "7" @default.
- W2554170757 startingPage "1" @default.
- W2554170757 abstract "In this work, we propose an unorthodox approach for describing a given image. Each image is represented by a feature vector whose elements are the scores assigned to object classes by deep convolutional neural networks that were not related to those that built the given image classification problem. The deep neural networks are trained using 1000 classes; therefore, each image is described by 1000 scores, which are fed to a support vector machine. The proposed approach could be considered a transfer learning method, where, instead of repurposing the learned features to a second classification problem, we use the scores obtained by trained convolutional neural networks. Methods based on state of the art handcrafted descriptors, and the novel approach presented here are compared, together with selected ensembles of such methods. The fusion between a standard approach and the new unorthodox method boosts the performance of the standard approach. The Wilcoxon signed rank test is used to compare the different methods. The novel method is applied to 21 different datasets to demonstrate its generality. The MATLAB source code to replicate our experiments will be available at (https://www.dei.unipd.it/node/2357 +Pattern Recognition and Ensemble Classifiers)." @default.
- W2554170757 created "2016-11-30" @default.
- W2554170757 creator A5007729428 @default.
- W2554170757 creator A5046852066 @default.
- W2554170757 date "2017-01-01" @default.
- W2554170757 modified "2023-10-01" @default.
- W2554170757 title "How could a subcellular image, or a painting by Van Gogh, be similar to a great white shark or to a pizza?" @default.
- W2554170757 cites W1524680991 @default.
- W2554170757 cites W1566135517 @default.
- W2554170757 cites W1825426646 @default.
- W2554170757 cites W1909952827 @default.
- W2554170757 cites W1968369572 @default.
- W2554170757 cites W2000266578 @default.
- W2554170757 cites W2002813366 @default.
- W2554170757 cites W2013300501 @default.
- W2554170757 cites W2020040086 @default.
- W2554170757 cites W2045258909 @default.
- W2554170757 cites W2046781710 @default.
- W2554170757 cites W2051864286 @default.
- W2554170757 cites W2056052642 @default.
- W2554170757 cites W2057624659 @default.
- W2554170757 cites W2062118960 @default.
- W2554170757 cites W2076063813 @default.
- W2554170757 cites W2113242816 @default.
- W2554170757 cites W2115629999 @default.
- W2554170757 cites W2136922672 @default.
- W2554170757 cites W2145752049 @default.
- W2554170757 cites W2151103935 @default.
- W2554170757 cites W2332352554 @default.
- W2554170757 cites W4248277245 @default.
- W2554170757 doi "https://doi.org/10.1016/j.patrec.2016.11.011" @default.
- W2554170757 hasPublicationYear "2017" @default.
- W2554170757 type Work @default.
- W2554170757 sameAs 2554170757 @default.
- W2554170757 citedByCount "20" @default.
- W2554170757 countsByYear W25541707572017 @default.
- W2554170757 countsByYear W25541707572018 @default.
- W2554170757 countsByYear W25541707572019 @default.
- W2554170757 countsByYear W25541707572020 @default.
- W2554170757 countsByYear W25541707572021 @default.
- W2554170757 countsByYear W25541707572022 @default.
- W2554170757 countsByYear W25541707572023 @default.
- W2554170757 crossrefType "journal-article" @default.
- W2554170757 hasAuthorship W2554170757A5007729428 @default.
- W2554170757 hasAuthorship W2554170757A5046852066 @default.
- W2554170757 hasConcept C105795698 @default.
- W2554170757 hasConcept C108583219 @default.
- W2554170757 hasConcept C114614502 @default.
- W2554170757 hasConcept C115961682 @default.
- W2554170757 hasConcept C119857082 @default.
- W2554170757 hasConcept C12267149 @default.
- W2554170757 hasConcept C12868164 @default.
- W2554170757 hasConcept C138885662 @default.
- W2554170757 hasConcept C153180895 @default.
- W2554170757 hasConcept C154945302 @default.
- W2554170757 hasConcept C15744967 @default.
- W2554170757 hasConcept C164226766 @default.
- W2554170757 hasConcept C177264268 @default.
- W2554170757 hasConcept C199360897 @default.
- W2554170757 hasConcept C206041023 @default.
- W2554170757 hasConcept C2776401178 @default.
- W2554170757 hasConcept C2776760102 @default.
- W2554170757 hasConcept C2780767217 @default.
- W2554170757 hasConcept C33923547 @default.
- W2554170757 hasConcept C41008148 @default.
- W2554170757 hasConcept C41895202 @default.
- W2554170757 hasConcept C50644808 @default.
- W2554170757 hasConcept C542102704 @default.
- W2554170757 hasConcept C75294576 @default.
- W2554170757 hasConcept C81363708 @default.
- W2554170757 hasConceptScore W2554170757C105795698 @default.
- W2554170757 hasConceptScore W2554170757C108583219 @default.
- W2554170757 hasConceptScore W2554170757C114614502 @default.
- W2554170757 hasConceptScore W2554170757C115961682 @default.
- W2554170757 hasConceptScore W2554170757C119857082 @default.
- W2554170757 hasConceptScore W2554170757C12267149 @default.
- W2554170757 hasConceptScore W2554170757C12868164 @default.
- W2554170757 hasConceptScore W2554170757C138885662 @default.
- W2554170757 hasConceptScore W2554170757C153180895 @default.
- W2554170757 hasConceptScore W2554170757C154945302 @default.
- W2554170757 hasConceptScore W2554170757C15744967 @default.
- W2554170757 hasConceptScore W2554170757C164226766 @default.
- W2554170757 hasConceptScore W2554170757C177264268 @default.
- W2554170757 hasConceptScore W2554170757C199360897 @default.
- W2554170757 hasConceptScore W2554170757C206041023 @default.
- W2554170757 hasConceptScore W2554170757C2776401178 @default.
- W2554170757 hasConceptScore W2554170757C2776760102 @default.
- W2554170757 hasConceptScore W2554170757C2780767217 @default.
- W2554170757 hasConceptScore W2554170757C33923547 @default.
- W2554170757 hasConceptScore W2554170757C41008148 @default.
- W2554170757 hasConceptScore W2554170757C41895202 @default.
- W2554170757 hasConceptScore W2554170757C50644808 @default.
- W2554170757 hasConceptScore W2554170757C542102704 @default.
- W2554170757 hasConceptScore W2554170757C75294576 @default.
- W2554170757 hasConceptScore W2554170757C81363708 @default.
- W2554170757 hasLocation W25541707571 @default.
- W2554170757 hasOpenAccess W2554170757 @default.
- W2554170757 hasPrimaryLocation W25541707571 @default.