FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136985054> ?p ?o ?g. }

• W3136985054 endingPage "1082" @default.
• W3136985054 startingPage "1082" @default.
• W3136985054 abstract "Deep convolutional neural networks (CNNs) are widely used in hyperspectral image (HSI) classification. However, the most successful CNN architectures are handcrafted, which need professional knowledge and consume a very significant amount of time. To automatically design cell-based CNN architectures for HSI classification, we propose an efficient continuous evolutionary method, named CPSO-Net, which can dramatically accelerate optimal architecture generation by the optimization of weight-sharing parameters. First, a SuperNet with all candidate operations is maintained to share the parameters for all individuals and optimized by collecting the gradients of all individuals in the population. Second, a novel direct encoding strategy is devised to encode architectures into particles, which inherit the parameters from the SuperNet. Then, particle swarm optimization is used to search for the optimal deep architecture from the particle swarm. Furthermore, experiments with limited training samples based on four widely used biased and unbiased hyperspectral datasets showed that our proposed method achieves good performance comparable to the state-of-the-art HSI classification methods." @default.
• W3136985054 created "2021-03-29" @default.
• W3136985054 creator A5025164229 @default.
• W3136985054 creator A5038861185 @default.
• W3136985054 creator A5040362491 @default.
• W3136985054 creator A5062400971 @default.
• W3136985054 creator A5078908602 @default.
• W3136985054 creator A5090090517 @default.
• W3136985054 date "2021-03-12" @default.
• W3136985054 modified "2023-10-18" @default.
• W3136985054 title "Continuous Particle Swarm Optimization-Based Deep Learning Architecture Search for Hyperspectral Image Classification" @default.
• W3136985054 cites W2008847349 @default.
• W3136985054 cites W2016944307 @default.
• W3136985054 cites W2018732570 @default.
• W3136985054 cites W2020399841 @default.
• W3136985054 cites W2028742169 @default.
• W3136985054 cites W2050870241 @default.
• W3136985054 cites W2097915756 @default.
• W3136985054 cites W2111935653 @default.
• W3136985054 cites W2119814172 @default.
• W3136985054 cites W2314785379 @default.
• W3136985054 cites W2500751094 @default.
• W3136985054 cites W2558391528 @default.
• W3136985054 cites W2572303978 @default.
• W3136985054 cites W2614166664 @default.
• W3136985054 cites W2740976805 @default.
• W3136985054 cites W2764276316 @default.
• W3136985054 cites W2799929262 @default.
• W3136985054 cites W2886682357 @default.
• W3136985054 cites W2892075618 @default.
• W3136985054 cites W2898312572 @default.
• W3136985054 cites W2900246877 @default.
• W3136985054 cites W2903452532 @default.
• W3136985054 cites W2908955282 @default.
• W3136985054 cites W2916206107 @default.
• W3136985054 cites W2928182459 @default.
• W3136985054 cites W2937638900 @default.
• W3136985054 cites W2940678725 @default.
• W3136985054 cites W2941141441 @default.
• W3136985054 cites W2943270518 @default.
• W3136985054 cites W2947137917 @default.
• W3136985054 cites W2966284335 @default.
• W3136985054 cites W2983327554 @default.
• W3136985054 cites W3003482697 @default.
• W3136985054 cites W3098561772 @default.
• W3136985054 doi "https://doi.org/10.3390/rs13061082" @default.
• W3136985054 hasPublicationYear "2021" @default.
• W3136985054 type Work @default.
• W3136985054 sameAs 3136985054 @default.
• W3136985054 citedByCount "15" @default.
• W3136985054 countsByYear W31369850542021 @default.
• W3136985054 countsByYear W31369850542022 @default.
• W3136985054 countsByYear W31369850542023 @default.
• W3136985054 crossrefType "journal-article" @default.
• W3136985054 hasAuthorship W3136985054A5025164229 @default.
• W3136985054 hasAuthorship W3136985054A5038861185 @default.
• W3136985054 hasAuthorship W3136985054A5040362491 @default.
• W3136985054 hasAuthorship W3136985054A5062400971 @default.
• W3136985054 hasAuthorship W3136985054A5078908602 @default.
• W3136985054 hasAuthorship W3136985054A5090090517 @default.
• W3136985054 hasBestOaLocation W31369850541 @default.
• W3136985054 hasConcept C104317684 @default.
• W3136985054 hasConcept C108583219 @default.
• W3136985054 hasConcept C119857082 @default.
• W3136985054 hasConcept C123657996 @default.
• W3136985054 hasConcept C144024400 @default.
• W3136985054 hasConcept C149923435 @default.
• W3136985054 hasConcept C153180895 @default.
• W3136985054 hasConcept C154945302 @default.
• W3136985054 hasConcept C159078339 @default.
• W3136985054 hasConcept C166957645 @default.
• W3136985054 hasConcept C185592680 @default.
• W3136985054 hasConcept C205649164 @default.
• W3136985054 hasConcept C2908647359 @default.
• W3136985054 hasConcept C41008148 @default.
• W3136985054 hasConcept C55493867 @default.
• W3136985054 hasConcept C66746571 @default.
• W3136985054 hasConcept C81363708 @default.
• W3136985054 hasConcept C85617194 @default.
• W3136985054 hasConceptScore W3136985054C104317684 @default.
• W3136985054 hasConceptScore W3136985054C108583219 @default.
• W3136985054 hasConceptScore W3136985054C119857082 @default.
• W3136985054 hasConceptScore W3136985054C123657996 @default.
• W3136985054 hasConceptScore W3136985054C144024400 @default.
• W3136985054 hasConceptScore W3136985054C149923435 @default.
• W3136985054 hasConceptScore W3136985054C153180895 @default.
• W3136985054 hasConceptScore W3136985054C154945302 @default.
• W3136985054 hasConceptScore W3136985054C159078339 @default.
• W3136985054 hasConceptScore W3136985054C166957645 @default.
• W3136985054 hasConceptScore W3136985054C185592680 @default.
• W3136985054 hasConceptScore W3136985054C205649164 @default.
• W3136985054 hasConceptScore W3136985054C2908647359 @default.
• W3136985054 hasConceptScore W3136985054C41008148 @default.
• W3136985054 hasConceptScore W3136985054C55493867 @default.
• W3136985054 hasConceptScore W3136985054C66746571 @default.
• W3136985054 hasConceptScore W3136985054C81363708 @default.
• W3136985054 hasConceptScore W3136985054C85617194 @default.
• W3136985054 hasIssue "6" @default.

• next