Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912288872> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2912288872 abstract "Single label image classification has been promisingly demonstrated using Convolutional Neural Network (CNN). However, how this CNN will fit for multi-label images is still difficult to solve. It is mainly difficult due to lack of multi-label training image data and high complexity of latent obj ect layouts. This paper proposes an approach for classifying multi-label image by a trained single label classifier using CNN with objectness measure and selective search. We have taken two established image segmentation techniques for segmenting a multi-label image into some segmented images. Then we have forwarded the images to our trained CNN and predicted the labels of the segmented images by generalizing the result. Our single-label image classifier gives 87% accuracy on CIFAR-10 dataset. Using objectness measure with CNN gives us 51 % accuracy on a multi-label dataset and gives up to 57% accuracy using selective search both considering top-4 labels that is significantly good for a simple approach rather than a complex approach for multi-label classification using CNN." @default.
- W2912288872 created "2019-02-21" @default.
- W2912288872 creator A5014285597 @default.
- W2912288872 creator A5050423427 @default.
- W2912288872 creator A5071178407 @default.
- W2912288872 creator A5078425375 @default.
- W2912288872 date "2018-12-01" @default.
- W2912288872 modified "2023-09-27" @default.
- W2912288872 title "An Approach for Multi Label Image Classification Using Single Label Convolutional Neural Network" @default.
- W2912288872 cites W1514027499 @default.
- W2912288872 cites W1567302070 @default.
- W2912288872 cites W1836465849 @default.
- W2912288872 cites W1905051261 @default.
- W2912288872 cites W1980061733 @default.
- W2912288872 cites W1999478155 @default.
- W2912288872 cites W2066624635 @default.
- W2912288872 cites W2088049833 @default.
- W2912288872 cites W2163605009 @default.
- W2912288872 cites W2463598282 @default.
- W2912288872 cites W2517498966 @default.
- W2912288872 doi "https://doi.org/10.1109/iccitechn.2018.8631970" @default.
- W2912288872 hasPublicationYear "2018" @default.
- W2912288872 type Work @default.
- W2912288872 sameAs 2912288872 @default.
- W2912288872 citedByCount "4" @default.
- W2912288872 countsByYear W29122888722020 @default.
- W2912288872 countsByYear W29122888722022 @default.
- W2912288872 crossrefType "proceedings-article" @default.
- W2912288872 hasAuthorship W2912288872A5014285597 @default.
- W2912288872 hasAuthorship W2912288872A5050423427 @default.
- W2912288872 hasAuthorship W2912288872A5071178407 @default.
- W2912288872 hasAuthorship W2912288872A5078425375 @default.
- W2912288872 hasConcept C115961682 @default.
- W2912288872 hasConcept C124504099 @default.
- W2912288872 hasConcept C153180895 @default.
- W2912288872 hasConcept C154945302 @default.
- W2912288872 hasConcept C2776482837 @default.
- W2912288872 hasConcept C31972630 @default.
- W2912288872 hasConcept C41008148 @default.
- W2912288872 hasConcept C50644808 @default.
- W2912288872 hasConcept C75294576 @default.
- W2912288872 hasConcept C81363708 @default.
- W2912288872 hasConcept C89600930 @default.
- W2912288872 hasConcept C95623464 @default.
- W2912288872 hasConceptScore W2912288872C115961682 @default.
- W2912288872 hasConceptScore W2912288872C124504099 @default.
- W2912288872 hasConceptScore W2912288872C153180895 @default.
- W2912288872 hasConceptScore W2912288872C154945302 @default.
- W2912288872 hasConceptScore W2912288872C2776482837 @default.
- W2912288872 hasConceptScore W2912288872C31972630 @default.
- W2912288872 hasConceptScore W2912288872C41008148 @default.
- W2912288872 hasConceptScore W2912288872C50644808 @default.
- W2912288872 hasConceptScore W2912288872C75294576 @default.
- W2912288872 hasConceptScore W2912288872C81363708 @default.
- W2912288872 hasConceptScore W2912288872C89600930 @default.
- W2912288872 hasConceptScore W2912288872C95623464 @default.
- W2912288872 hasLocation W29122888721 @default.
- W2912288872 hasOpenAccess W2912288872 @default.
- W2912288872 hasPrimaryLocation W29122888721 @default.
- W2912288872 hasRelatedWork W2415731916 @default.
- W2912288872 hasRelatedWork W2563096758 @default.
- W2912288872 hasRelatedWork W2766500168 @default.
- W2912288872 hasRelatedWork W2885073348 @default.
- W2912288872 hasRelatedWork W2912288872 @default.
- W2912288872 hasRelatedWork W2944354449 @default.
- W2912288872 hasRelatedWork W2994347668 @default.
- W2912288872 hasRelatedWork W3095523211 @default.
- W2912288872 hasRelatedWork W3208337204 @default.
- W2912288872 hasRelatedWork W4225852842 @default.
- W2912288872 isParatext "false" @default.
- W2912288872 isRetracted "false" @default.
- W2912288872 magId "2912288872" @default.
- W2912288872 workType "article" @default.