Matches in SemOpenAlex for { <https://semopenalex.org/work/W2941338873> ?p ?o ?g. }
- W2941338873 abstract "The Convolution Neural Network(CNN) has achieved great performance in image classification, partially due to the deeper and deeper structure. While its complexity brings more challenge to the practical application. So we can design a more efficient loss function to get better results without a more complex network. In this paper, we proposed a weighted softmax loss function called confusion weighted loss to learn the relationship among the confusing categories. Firstly, we generate a similarity matrix based on the confusion matrix to illustrate the relationship among the categories. Then, we propose a clustering algorithm to find out the confusing categories. Finally, to learn more information among them, we design a weighted matrix used in our loss function. Experiments on different datasets demonstrate the effectiveness of our method." @default.
- W2941338873 created "2019-05-03" @default.
- W2941338873 creator A5000427803 @default.
- W2941338873 creator A5002120153 @default.
- W2941338873 creator A5046229888 @default.
- W2941338873 creator A5051987502 @default.
- W2941338873 creator A5056136429 @default.
- W2941338873 date "2018-12-01" @default.
- W2941338873 modified "2023-09-23" @default.
- W2941338873 title "Confusion Weighted Loss for Ambiguous Classification" @default.
- W2941338873 cites W1898560071 @default.
- W2941338873 cites W2037456689 @default.
- W2941338873 cites W2094618318 @default.
- W2941338873 cites W2097117768 @default.
- W2941338873 cites W2107034620 @default.
- W2941338873 cites W2113855951 @default.
- W2941338873 cites W2134670479 @default.
- W2941338873 cites W2152161678 @default.
- W2941338873 cites W2163605009 @default.
- W2941338873 cites W2166761907 @default.
- W2941338873 cites W2168356304 @default.
- W2941338873 cites W2194775991 @default.
- W2941338873 cites W2527800741 @default.
- W2941338873 cites W2952271367 @default.
- W2941338873 cites W2964350570 @default.
- W2941338873 cites W3099206234 @default.
- W2941338873 doi "https://doi.org/10.1109/vcip.2018.8698693" @default.
- W2941338873 hasPublicationYear "2018" @default.
- W2941338873 type Work @default.
- W2941338873 sameAs 2941338873 @default.
- W2941338873 citedByCount "1" @default.
- W2941338873 countsByYear W29413388732021 @default.
- W2941338873 crossrefType "proceedings-article" @default.
- W2941338873 hasAuthorship W2941338873A5000427803 @default.
- W2941338873 hasAuthorship W2941338873A5002120153 @default.
- W2941338873 hasAuthorship W2941338873A5046229888 @default.
- W2941338873 hasAuthorship W2941338873A5051987502 @default.
- W2941338873 hasAuthorship W2941338873A5056136429 @default.
- W2941338873 hasConcept C103278499 @default.
- W2941338873 hasConcept C106487976 @default.
- W2941338873 hasConcept C11171543 @default.
- W2941338873 hasConcept C11413529 @default.
- W2941338873 hasConcept C115961682 @default.
- W2941338873 hasConcept C119857082 @default.
- W2941338873 hasConcept C124101348 @default.
- W2941338873 hasConcept C138602881 @default.
- W2941338873 hasConcept C14036430 @default.
- W2941338873 hasConcept C153180895 @default.
- W2941338873 hasConcept C154945302 @default.
- W2941338873 hasConcept C15744967 @default.
- W2941338873 hasConcept C159985019 @default.
- W2941338873 hasConcept C188441871 @default.
- W2941338873 hasConcept C192562407 @default.
- W2941338873 hasConcept C2781140086 @default.
- W2941338873 hasConcept C41008148 @default.
- W2941338873 hasConcept C45347329 @default.
- W2941338873 hasConcept C50644808 @default.
- W2941338873 hasConcept C73555534 @default.
- W2941338873 hasConcept C78458016 @default.
- W2941338873 hasConcept C81363708 @default.
- W2941338873 hasConcept C86803240 @default.
- W2941338873 hasConceptScore W2941338873C103278499 @default.
- W2941338873 hasConceptScore W2941338873C106487976 @default.
- W2941338873 hasConceptScore W2941338873C11171543 @default.
- W2941338873 hasConceptScore W2941338873C11413529 @default.
- W2941338873 hasConceptScore W2941338873C115961682 @default.
- W2941338873 hasConceptScore W2941338873C119857082 @default.
- W2941338873 hasConceptScore W2941338873C124101348 @default.
- W2941338873 hasConceptScore W2941338873C138602881 @default.
- W2941338873 hasConceptScore W2941338873C14036430 @default.
- W2941338873 hasConceptScore W2941338873C153180895 @default.
- W2941338873 hasConceptScore W2941338873C154945302 @default.
- W2941338873 hasConceptScore W2941338873C15744967 @default.
- W2941338873 hasConceptScore W2941338873C159985019 @default.
- W2941338873 hasConceptScore W2941338873C188441871 @default.
- W2941338873 hasConceptScore W2941338873C192562407 @default.
- W2941338873 hasConceptScore W2941338873C2781140086 @default.
- W2941338873 hasConceptScore W2941338873C41008148 @default.
- W2941338873 hasConceptScore W2941338873C45347329 @default.
- W2941338873 hasConceptScore W2941338873C50644808 @default.
- W2941338873 hasConceptScore W2941338873C73555534 @default.
- W2941338873 hasConceptScore W2941338873C78458016 @default.
- W2941338873 hasConceptScore W2941338873C81363708 @default.
- W2941338873 hasConceptScore W2941338873C86803240 @default.
- W2941338873 hasLocation W29413388731 @default.
- W2941338873 hasOpenAccess W2941338873 @default.
- W2941338873 hasPrimaryLocation W29413388731 @default.
- W2941338873 hasRelatedWork W2125635584 @default.
- W2941338873 hasRelatedWork W2588607706 @default.
- W2941338873 hasRelatedWork W2613736958 @default.
- W2941338873 hasRelatedWork W2621864722 @default.
- W2941338873 hasRelatedWork W2758063741 @default.
- W2941338873 hasRelatedWork W2876477761 @default.
- W2941338873 hasRelatedWork W2909857627 @default.
- W2941338873 hasRelatedWork W2963480192 @default.
- W2941338873 hasRelatedWork W2977314777 @default.
- W2941338873 hasRelatedWork W4283328168 @default.
- W2941338873 isParatext "false" @default.
- W2941338873 isRetracted "false" @default.
- W2941338873 magId "2941338873" @default.