Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089661409> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3089661409 endingPage "192" @default.
- W3089661409 startingPage "186" @default.
- W3089661409 abstract "Remote sensing image scene classification (RSISC) is one of the bases of visual question answering for remote sensing data (RSVQA). In the conventional deep learning based solutions of RSISC, domain experts have to manually design the neural architecture, which is costly in both time and manpower. In this paper, AutoRSISC, a high resolution remote sensing image scene classification method based on neural architecture search (NAS) is proposed. AutoRSISC algorithm samples the neural architecture in a certain proportion to reduce the redundancy in the search space which is based on the continuous relaxation of the neural architecture representation. Edge normalization is introduced to make architecture search more efficient. The conventional deep learning approaches take days or more just to manually design the appropriate neural architecture according to the current data set. The experimental results show that our method saves time and manpower compared with the existing manually designed RSISC methods. Our AutoRSISC algorithm took 7.6 h from the automatic design of the most appropriate neural architecture to the end of all experiments according to the UCM data set, and the classification accuracy rate of the final test set reached 97.85%. And our AutoRSISC algorithm took 101.7 h from the automatic design of the most appropriate neural architecture to the end of all experiments according to the NWPU45 data set, and the classification accuracy rate of the final test set reached 94.66%." @default.
- W3089661409 created "2020-10-08" @default.
- W3089661409 creator A5006653425 @default.
- W3089661409 creator A5074535695 @default.
- W3089661409 creator A5075729645 @default.
- W3089661409 creator A5079301418 @default.
- W3089661409 date "2020-12-01" @default.
- W3089661409 modified "2023-10-06" @default.
- W3089661409 title "AutoRSISC: Automatic design of neural architecture for remote sensing image scene classification" @default.
- W3089661409 cites W1958291604 @default.
- W3089661409 cites W2006603039 @default.
- W3089661409 cites W2064630666 @default.
- W3089661409 cites W2098676252 @default.
- W3089661409 cites W2100495367 @default.
- W3089661409 cites W2147141800 @default.
- W3089661409 cites W2253590344 @default.
- W3089661409 cites W2291068538 @default.
- W3089661409 cites W2618530766 @default.
- W3089661409 cites W2715220489 @default.
- W3089661409 cites W2783165089 @default.
- W3089661409 cites W2806299729 @default.
- W3089661409 cites W2829067510 @default.
- W3089661409 cites W2897086142 @default.
- W3089661409 cites W2981445785 @default.
- W3089661409 cites W3103856189 @default.
- W3089661409 doi "https://doi.org/10.1016/j.patrec.2020.09.034" @default.
- W3089661409 hasPublicationYear "2020" @default.
- W3089661409 type Work @default.
- W3089661409 sameAs 3089661409 @default.
- W3089661409 citedByCount "17" @default.
- W3089661409 countsByYear W30896614092021 @default.
- W3089661409 countsByYear W30896614092022 @default.
- W3089661409 countsByYear W30896614092023 @default.
- W3089661409 crossrefType "journal-article" @default.
- W3089661409 hasAuthorship W3089661409A5006653425 @default.
- W3089661409 hasAuthorship W3089661409A5074535695 @default.
- W3089661409 hasAuthorship W3089661409A5075729645 @default.
- W3089661409 hasAuthorship W3089661409A5079301418 @default.
- W3089661409 hasConcept C111919701 @default.
- W3089661409 hasConcept C115961682 @default.
- W3089661409 hasConcept C123657996 @default.
- W3089661409 hasConcept C124101348 @default.
- W3089661409 hasConcept C136886441 @default.
- W3089661409 hasConcept C142362112 @default.
- W3089661409 hasConcept C144024400 @default.
- W3089661409 hasConcept C152124472 @default.
- W3089661409 hasConcept C153180895 @default.
- W3089661409 hasConcept C153349607 @default.
- W3089661409 hasConcept C154945302 @default.
- W3089661409 hasConcept C16910744 @default.
- W3089661409 hasConcept C169903167 @default.
- W3089661409 hasConcept C177264268 @default.
- W3089661409 hasConcept C19165224 @default.
- W3089661409 hasConcept C199360897 @default.
- W3089661409 hasConcept C41008148 @default.
- W3089661409 hasConcept C50644808 @default.
- W3089661409 hasConcept C58489278 @default.
- W3089661409 hasConcept C75294576 @default.
- W3089661409 hasConceptScore W3089661409C111919701 @default.
- W3089661409 hasConceptScore W3089661409C115961682 @default.
- W3089661409 hasConceptScore W3089661409C123657996 @default.
- W3089661409 hasConceptScore W3089661409C124101348 @default.
- W3089661409 hasConceptScore W3089661409C136886441 @default.
- W3089661409 hasConceptScore W3089661409C142362112 @default.
- W3089661409 hasConceptScore W3089661409C144024400 @default.
- W3089661409 hasConceptScore W3089661409C152124472 @default.
- W3089661409 hasConceptScore W3089661409C153180895 @default.
- W3089661409 hasConceptScore W3089661409C153349607 @default.
- W3089661409 hasConceptScore W3089661409C154945302 @default.
- W3089661409 hasConceptScore W3089661409C16910744 @default.
- W3089661409 hasConceptScore W3089661409C169903167 @default.
- W3089661409 hasConceptScore W3089661409C177264268 @default.
- W3089661409 hasConceptScore W3089661409C19165224 @default.
- W3089661409 hasConceptScore W3089661409C199360897 @default.
- W3089661409 hasConceptScore W3089661409C41008148 @default.
- W3089661409 hasConceptScore W3089661409C50644808 @default.
- W3089661409 hasConceptScore W3089661409C58489278 @default.
- W3089661409 hasConceptScore W3089661409C75294576 @default.
- W3089661409 hasFunder F4320321001 @default.
- W3089661409 hasFunder F4320335787 @default.
- W3089661409 hasLocation W30896614091 @default.
- W3089661409 hasOpenAccess W3089661409 @default.
- W3089661409 hasPrimaryLocation W30896614091 @default.
- W3089661409 hasRelatedWork W1574942924 @default.
- W3089661409 hasRelatedWork W2027071967 @default.
- W3089661409 hasRelatedWork W2028462208 @default.
- W3089661409 hasRelatedWork W2187490799 @default.
- W3089661409 hasRelatedWork W2363004085 @default.
- W3089661409 hasRelatedWork W2982831492 @default.
- W3089661409 hasRelatedWork W3019226033 @default.
- W3089661409 hasRelatedWork W3094735304 @default.
- W3089661409 hasRelatedWork W3138055416 @default.
- W3089661409 hasRelatedWork W4285337533 @default.
- W3089661409 hasVolume "140" @default.
- W3089661409 isParatext "false" @default.
- W3089661409 isRetracted "false" @default.
- W3089661409 magId "3089661409" @default.
- W3089661409 workType "article" @default.