Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902587811> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2902587811 abstract "The success of deep neural networks depends strongly on the availability of balanced and well-refined datasets, but in a real industry or practical cases, it is difficult to create such a dataset. In this paper, we present an approach to effectively use a highly imbalanced, hierarchically dual-labeled and multi-channel dataset: 1) using difference images, 2) transfer learning, 3) data argumentation and 4) DNN model based on an autoencoder which has the same number of bottleneck nodes as the number of classes. We evaluate our approach on the HDI AFVI dataset, containing ~65k 4 channel images, 37 classes, and dual-labeled for each 36 defective class. The result demonstrates the effectiveness of our proposed methods in realistic settings." @default.
- W2902587811 created "2018-12-11" @default.
- W2902587811 creator A5003317804 @default.
- W2902587811 creator A5003346555 @default.
- W2902587811 creator A5012239261 @default.
- W2902587811 creator A5044320085 @default.
- W2902587811 creator A5084478127 @default.
- W2902587811 date "2018-06-01" @default.
- W2902587811 modified "2023-10-12" @default.
- W2902587811 title "Learning from Imbalanced and Hierarchically Dual-Labeled Data" @default.
- W2902587811 cites W2163605009 @default.
- W2902587811 cites W2194775991 @default.
- W2902587811 cites W2274287116 @default.
- W2902587811 cites W2302255633 @default.
- W2902587811 cites W2962835968 @default.
- W2902587811 cites W2962971773 @default.
- W2902587811 cites W3118608800 @default.
- W2902587811 doi "https://doi.org/10.1109/icce-asia.2018.8552126" @default.
- W2902587811 hasPublicationYear "2018" @default.
- W2902587811 type Work @default.
- W2902587811 sameAs 2902587811 @default.
- W2902587811 citedByCount "0" @default.
- W2902587811 crossrefType "proceedings-article" @default.
- W2902587811 hasAuthorship W2902587811A5003317804 @default.
- W2902587811 hasAuthorship W2902587811A5003346555 @default.
- W2902587811 hasAuthorship W2902587811A5012239261 @default.
- W2902587811 hasAuthorship W2902587811A5044320085 @default.
- W2902587811 hasAuthorship W2902587811A5084478127 @default.
- W2902587811 hasConcept C101738243 @default.
- W2902587811 hasConcept C108583219 @default.
- W2902587811 hasConcept C119857082 @default.
- W2902587811 hasConcept C124101348 @default.
- W2902587811 hasConcept C124952713 @default.
- W2902587811 hasConcept C127162648 @default.
- W2902587811 hasConcept C142362112 @default.
- W2902587811 hasConcept C149635348 @default.
- W2902587811 hasConcept C150899416 @default.
- W2902587811 hasConcept C152139883 @default.
- W2902587811 hasConcept C153180895 @default.
- W2902587811 hasConcept C154945302 @default.
- W2902587811 hasConcept C2777212361 @default.
- W2902587811 hasConcept C2780513914 @default.
- W2902587811 hasConcept C2780980858 @default.
- W2902587811 hasConcept C31258907 @default.
- W2902587811 hasConcept C41008148 @default.
- W2902587811 hasConcept C50644808 @default.
- W2902587811 hasConcept C60008888 @default.
- W2902587811 hasConceptScore W2902587811C101738243 @default.
- W2902587811 hasConceptScore W2902587811C108583219 @default.
- W2902587811 hasConceptScore W2902587811C119857082 @default.
- W2902587811 hasConceptScore W2902587811C124101348 @default.
- W2902587811 hasConceptScore W2902587811C124952713 @default.
- W2902587811 hasConceptScore W2902587811C127162648 @default.
- W2902587811 hasConceptScore W2902587811C142362112 @default.
- W2902587811 hasConceptScore W2902587811C149635348 @default.
- W2902587811 hasConceptScore W2902587811C150899416 @default.
- W2902587811 hasConceptScore W2902587811C152139883 @default.
- W2902587811 hasConceptScore W2902587811C153180895 @default.
- W2902587811 hasConceptScore W2902587811C154945302 @default.
- W2902587811 hasConceptScore W2902587811C2777212361 @default.
- W2902587811 hasConceptScore W2902587811C2780513914 @default.
- W2902587811 hasConceptScore W2902587811C2780980858 @default.
- W2902587811 hasConceptScore W2902587811C31258907 @default.
- W2902587811 hasConceptScore W2902587811C41008148 @default.
- W2902587811 hasConceptScore W2902587811C50644808 @default.
- W2902587811 hasConceptScore W2902587811C60008888 @default.
- W2902587811 hasLocation W29025878111 @default.
- W2902587811 hasOpenAccess W2902587811 @default.
- W2902587811 hasPrimaryLocation W29025878111 @default.
- W2902587811 hasRelatedWork W1990975532 @default.
- W2902587811 hasRelatedWork W1998565453 @default.
- W2902587811 hasRelatedWork W2099352187 @default.
- W2902587811 hasRelatedWork W2205224283 @default.
- W2902587811 hasRelatedWork W2811444512 @default.
- W2902587811 hasRelatedWork W2845604977 @default.
- W2902587811 hasRelatedWork W2946215091 @default.
- W2902587811 hasRelatedWork W2952435325 @default.
- W2902587811 hasRelatedWork W2982650666 @default.
- W2902587811 hasRelatedWork W3023856843 @default.
- W2902587811 hasRelatedWork W3084411871 @default.
- W2902587811 hasRelatedWork W3088965095 @default.
- W2902587811 hasRelatedWork W3096461453 @default.
- W2902587811 hasRelatedWork W3106400857 @default.
- W2902587811 hasRelatedWork W3143586484 @default.
- W2902587811 hasRelatedWork W3172882195 @default.
- W2902587811 hasRelatedWork W3176782276 @default.
- W2902587811 hasRelatedWork W3177628004 @default.
- W2902587811 hasRelatedWork W3205830981 @default.
- W2902587811 hasRelatedWork W831907635 @default.
- W2902587811 isParatext "false" @default.
- W2902587811 isRetracted "false" @default.
- W2902587811 magId "2902587811" @default.
- W2902587811 workType "article" @default.