Matches in SemOpenAlex for { <https://semopenalex.org/work/W2911810010> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2911810010 endingPage "206" @default.
- W2911810010 startingPage "191" @default.
- W2911810010 abstract "Abstract Scene classification is a significant aspect of computer vision. Convolutional neural networks (CNNs), a development of deep learning, are a well-understood tool for image classification. But training CNNs requires large-scale datasets. Transfer learning addresses this problem and produces a solution for small-scale datasets. Because scene image classification is more complex than common image classification. We propose a novel ResNet based transfer learning model utilizing multi-layer feature fusion, taking full advantage of interlayer discriminating features and fusing them for classification by softmax regression. In addition, a novel data augmentation method with a filter useful for small-scale datasets is presented. New image patches are generated by sliding block cropping of a raw image, which are then filtered to insure that the new images sufficiently represent the original categorization. Our new ResNet based transfer learning model with enhanced data augmentation is evaluated on six benchmark scene datasets (LF, OT, FP, LS, MIT67, SUN397). Extensive experimental results show that on the six datasets our method obtains better accuracy than other state-of-the-art models." @default.
- W2911810010 created "2019-02-21" @default.
- W2911810010 creator A5006536923 @default.
- W2911810010 creator A5027398178 @default.
- W2911810010 creator A5047774700 @default.
- W2911810010 date "2019-04-01" @default.
- W2911810010 modified "2023-10-12" @default.
- W2911810010 title "A novel scene classification model combining ResNet based transfer learning and data augmentation with a filter" @default.
- W2911810010 cites W1496239851 @default.
- W2911810010 cites W1566135517 @default.
- W2911810010 cites W1628899544 @default.
- W2911810010 cites W1970323662 @default.
- W2911810010 cites W1985506318 @default.
- W2911810010 cites W2013044826 @default.
- W2911810010 cites W2027444427 @default.
- W2911810010 cites W2031489346 @default.
- W2911810010 cites W2040999325 @default.
- W2911810010 cites W2071238245 @default.
- W2911810010 cites W2089660351 @default.
- W2911810010 cites W2094618318 @default.
- W2911810010 cites W2110628941 @default.
- W2911810010 cites W2112796928 @default.
- W2911810010 cites W2113855951 @default.
- W2911810010 cites W2115403315 @default.
- W2911810010 cites W2121707160 @default.
- W2911810010 cites W2125574651 @default.
- W2911810010 cites W2127807804 @default.
- W2911810010 cites W2147800946 @default.
- W2911810010 cites W2151103935 @default.
- W2911810010 cites W2165698076 @default.
- W2911810010 cites W2172490184 @default.
- W2911810010 cites W2253429366 @default.
- W2911810010 cites W2258484932 @default.
- W2911810010 cites W2259677467 @default.
- W2911810010 cites W2395579298 @default.
- W2911810010 cites W2512115693 @default.
- W2911810010 cites W2554078916 @default.
- W2911810010 cites W2559881210 @default.
- W2911810010 cites W2567001798 @default.
- W2911810010 cites W2592659495 @default.
- W2911810010 cites W2730200455 @default.
- W2911810010 cites W2755125693 @default.
- W2911810010 cites W2767432184 @default.
- W2911810010 cites W2773723772 @default.
- W2911810010 cites W2789571202 @default.
- W2911810010 cites W3101522362 @default.
- W2911810010 doi "https://doi.org/10.1016/j.neucom.2019.01.090" @default.
- W2911810010 hasPublicationYear "2019" @default.
- W2911810010 type Work @default.
- W2911810010 sameAs 2911810010 @default.
- W2911810010 citedByCount "91" @default.
- W2911810010 countsByYear W29118100102019 @default.
- W2911810010 countsByYear W29118100102020 @default.
- W2911810010 countsByYear W29118100102021 @default.
- W2911810010 countsByYear W29118100102022 @default.
- W2911810010 countsByYear W29118100102023 @default.
- W2911810010 crossrefType "journal-article" @default.
- W2911810010 hasAuthorship W2911810010A5006536923 @default.
- W2911810010 hasAuthorship W2911810010A5027398178 @default.
- W2911810010 hasAuthorship W2911810010A5047774700 @default.
- W2911810010 hasConcept C106131492 @default.
- W2911810010 hasConcept C108583219 @default.
- W2911810010 hasConcept C119857082 @default.
- W2911810010 hasConcept C150899416 @default.
- W2911810010 hasConcept C153180895 @default.
- W2911810010 hasConcept C154945302 @default.
- W2911810010 hasConcept C2944601119 @default.
- W2911810010 hasConcept C31972630 @default.
- W2911810010 hasConcept C41008148 @default.
- W2911810010 hasConceptScore W2911810010C106131492 @default.
- W2911810010 hasConceptScore W2911810010C108583219 @default.
- W2911810010 hasConceptScore W2911810010C119857082 @default.
- W2911810010 hasConceptScore W2911810010C150899416 @default.
- W2911810010 hasConceptScore W2911810010C153180895 @default.
- W2911810010 hasConceptScore W2911810010C154945302 @default.
- W2911810010 hasConceptScore W2911810010C2944601119 @default.
- W2911810010 hasConceptScore W2911810010C31972630 @default.
- W2911810010 hasConceptScore W2911810010C41008148 @default.
- W2911810010 hasFunder F4320321001 @default.
- W2911810010 hasLocation W29118100101 @default.
- W2911810010 hasOpenAccess W2911810010 @default.
- W2911810010 hasPrimaryLocation W29118100101 @default.
- W2911810010 hasRelatedWork W2960456850 @default.
- W2911810010 hasRelatedWork W3021430260 @default.
- W2911810010 hasRelatedWork W3133293092 @default.
- W2911810010 hasRelatedWork W4281382123 @default.
- W2911810010 hasRelatedWork W4281645081 @default.
- W2911810010 hasRelatedWork W4294306704 @default.
- W2911810010 hasRelatedWork W4308262314 @default.
- W2911810010 hasRelatedWork W4313050734 @default.
- W2911810010 hasRelatedWork W4318834068 @default.
- W2911810010 hasRelatedWork W4318957922 @default.
- W2911810010 hasVolume "338" @default.
- W2911810010 isParatext "false" @default.
- W2911810010 isRetracted "false" @default.
- W2911810010 magId "2911810010" @default.
- W2911810010 workType "article" @default.