FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938366133> ?p ?o ?g. }

• W2938366133 endingPage "3367" @default.
• W2938366133 startingPage "3345" @default.
• W2938366133 abstract "The convolutional neural networks (CNN) applied in remote sensing scene classification have two common problems. One is that these models have large number of parameters, which causes over-fitting easily. The other is that the network is not deep enough, thus more abstract semantic information cannot be extracted. To solve these two problems, we propose a simple and efficient full convolutional network based on DenseNet for remote sensing scene classification. We construct a small number of convolutional kernels to generate a large number of reusable feature maps by dense connections, which makes the network deeper, but does not increase the number of parameters significantly. Our network is so deep that it has more than 100 layers. However, it has only about 7 million parameters, which is far less than the number of VGGos parameters. Then we incorporate an adaptive average 3D pooling operation in our network. This operation fixes feature maps of size 7 × 7 from the last DenseBlock to 1 × 1 and decreases the number of channels from 1024 to 512, thus the whole network can accept input images with different sizes. Furthermore, we design the convolutional layer instead of the fully connected layer that is used as a classifier usually, so that the output features of the network can be classified without flattening operation, which simplifies the classification operation. Finally, a good model is trained by exploiting pre-trained weights and data augmentation technology. Compared with several state-of-the-art algorithms, our algorithm improves classification performance significantly on UCM dataset, AID dataset, OPTIMAL-31 dataset and NWPU-RESISC45 dataset." @default.
• W2938366133 created "2019-04-25" @default.
• W2938366133 creator A5018244700 @default.
• W2938366133 creator A5022746945 @default.
• W2938366133 creator A5039271899 @default.
• W2938366133 creator A5067580558 @default.
• W2938366133 creator A5077592935 @default.
• W2938366133 date "2019-01-01" @default.
• W2938366133 modified "2023-10-17" @default.
• W2938366133 title "A full convolutional network based on DenseNet for remote sensing scene classification" @default.
• W2938366133 cites W1912954554 @default.
• W2938366133 cites W1967865200 @default.
• W2938366133 cites W1972172639 @default.
• W2938366133 cites W1980038761 @default.
• W2938366133 cites W1989316905 @default.
• W2938366133 cites W2015386604 @default.
• W2938366133 cites W2024815898 @default.
• W2938366133 cites W2040648426 @default.
• W2938366133 cites W2064125725 @default.
• W2938366133 cites W2077689834 @default.
• W2938366133 cites W2104520867 @default.
• W2938366133 cites W2117539524 @default.
• W2938366133 cites W2153425333 @default.
• W2938366133 cites W2253590344 @default.
• W2938366133 cites W2331143823 @default.
• W2938366133 cites W2342880667 @default.
• W2938366133 cites W2470786530 @default.
• W2938366133 cites W2512351403 @default.
• W2938366133 cites W258213556 @default.
• W2938366133 cites W2607558879 @default.
• W2938366133 cites W2620429297 @default.
• W2938366133 cites W2735937663 @default.
• W2938366133 cites W2783165089 @default.
• W2938366133 cites W2801521191 @default.
• W2938366133 cites W2890732922 @default.
• W2938366133 cites W2897550403 @default.
• W2938366133 cites W2908997014 @default.
• W2938366133 cites W2910673922 @default.
• W2938366133 cites W2911268982 @default.
• W2938366133 cites W2949117887 @default.
• W2938366133 cites W2963446712 @default.
• W2938366133 cites W3103856189 @default.
• W2938366133 cites W3105577662 @default.
• W2938366133 cites W40885937 @default.
• W2938366133 doi "https://doi.org/10.3934/mbe.2019167" @default.
• W2938366133 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31499617" @default.
• W2938366133 hasPublicationYear "2019" @default.
• W2938366133 type Work @default.
• W2938366133 sameAs 2938366133 @default.
• W2938366133 citedByCount "113" @default.
• W2938366133 countsByYear W29383661332019 @default.
• W2938366133 countsByYear W29383661332020 @default.
• W2938366133 countsByYear W29383661332021 @default.
• W2938366133 countsByYear W29383661332022 @default.
• W2938366133 countsByYear W29383661332023 @default.
• W2938366133 crossrefType "journal-article" @default.
• W2938366133 hasAuthorship W2938366133A5018244700 @default.
• W2938366133 hasAuthorship W2938366133A5022746945 @default.
• W2938366133 hasAuthorship W2938366133A5039271899 @default.
• W2938366133 hasAuthorship W2938366133A5067580558 @default.
• W2938366133 hasAuthorship W2938366133A5077592935 @default.
• W2938366133 hasBestOaLocation W29383661331 @default.
• W2938366133 hasConcept C115961682 @default.
• W2938366133 hasConcept C124101348 @default.
• W2938366133 hasConcept C138885662 @default.
• W2938366133 hasConcept C153180895 @default.
• W2938366133 hasConcept C154945302 @default.
• W2938366133 hasConcept C159985019 @default.
• W2938366133 hasConcept C192562407 @default.
• W2938366133 hasConcept C19444555 @default.
• W2938366133 hasConcept C2776401178 @default.
• W2938366133 hasConcept C41008148 @default.
• W2938366133 hasConcept C41895202 @default.
• W2938366133 hasConcept C70437156 @default.
• W2938366133 hasConcept C75294576 @default.
• W2938366133 hasConcept C81363708 @default.
• W2938366133 hasConcept C95623464 @default.
• W2938366133 hasConceptScore W2938366133C115961682 @default.
• W2938366133 hasConceptScore W2938366133C124101348 @default.
• W2938366133 hasConceptScore W2938366133C138885662 @default.
• W2938366133 hasConceptScore W2938366133C153180895 @default.
• W2938366133 hasConceptScore W2938366133C154945302 @default.
• W2938366133 hasConceptScore W2938366133C159985019 @default.
• W2938366133 hasConceptScore W2938366133C192562407 @default.
• W2938366133 hasConceptScore W2938366133C19444555 @default.
• W2938366133 hasConceptScore W2938366133C2776401178 @default.
• W2938366133 hasConceptScore W2938366133C41008148 @default.
• W2938366133 hasConceptScore W2938366133C41895202 @default.
• W2938366133 hasConceptScore W2938366133C70437156 @default.
• W2938366133 hasConceptScore W2938366133C75294576 @default.
• W2938366133 hasConceptScore W2938366133C81363708 @default.
• W2938366133 hasConceptScore W2938366133C95623464 @default.
• W2938366133 hasIssue "5" @default.
• W2938366133 hasLocation W29383661331 @default.
• W2938366133 hasLocation W29383661332 @default.
• W2938366133 hasLocation W29383661333 @default.
• W2938366133 hasOpenAccess W2938366133 @default.
• W2938366133 hasPrimaryLocation W29383661331 @default.

• next