Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804902458> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2804902458 endingPage "1258" @default.
- W2804902458 startingPage "1254" @default.
- W2804902458 abstract "Convolutional neural networks (CNNs) have recently been demonstrated to be a powerful tool for hyperspectral image (HSI) classification, since they adopt deep convolutional layers whose kernels can effectively extract high-level spatial–spectral features. However, sampling locations of traditional convolutional kernels are fixed and cannot be changed according to complex spatial structures in HSIs. In addition, the typical pooling layers (e.g., average or maximum operations) in CNNs are also fixed and cannot be learned for feature downsampling in an adaptive manner. In this letter, a novel deformable CNN-based HSI classification method is proposed, which is called deformable HSI classification networks (DHCNet). The proposed network, DHCNet, introduces the deformable convolutional sampling locations, whose size and shape can be adaptively adjusted according to HSIs’ complex spatial contexts. Specifically, to create the deformable sampling locations, 2-D offsets are first calculated for each pixel of input images. The sampling locations of each pixel with calculated offsets can cover the locations of other neighboring pixels with similar characteristics. With the deformable sampling locations, deformable feature images are then created by compressing neighboring similar structural information of each pixel into fixed grids. Therefore, applying the regular convolutions on the deformable feature images can reflect complex structures more effectively. Moreover, instead of adopting the pooling layers, the strided convolution is further introduced on the feature images, which can be learned for feature downsampling according to spatial contexts. Experimental results on two real HSI data sets demonstrate that DHCNet can obtain better classification performance than can several well-known classification methods." @default.
- W2804902458 created "2018-06-01" @default.
- W2804902458 creator A5039993720 @default.
- W2804902458 creator A5065061505 @default.
- W2804902458 creator A5074919292 @default.
- W2804902458 date "2018-08-01" @default.
- W2804902458 modified "2023-10-16" @default.
- W2804902458 title "Deformable Convolutional Neural Networks for Hyperspectral Image Classification" @default.
- W2804902458 cites W1567302070 @default.
- W2804902458 cites W1939429412 @default.
- W2804902458 cites W2035057253 @default.
- W2804902458 cites W2041100636 @default.
- W2804902458 cites W2045757377 @default.
- W2804902458 cites W2053615857 @default.
- W2804902458 cites W2101365302 @default.
- W2804902458 cites W2136251662 @default.
- W2804902458 cites W2158400785 @default.
- W2804902458 cites W2166923144 @default.
- W2804902458 cites W2500751094 @default.
- W2804902458 cites W2512351403 @default.
- W2804902458 cites W2582369608 @default.
- W2804902458 cites W2595902385 @default.
- W2804902458 cites W2601564443 @default.
- W2804902458 cites W2606929568 @default.
- W2804902458 cites W2744582969 @default.
- W2804902458 cites W2750085043 @default.
- W2804902458 cites W2763731268 @default.
- W2804902458 cites W2768211636 @default.
- W2804902458 cites W2793645503 @default.
- W2804902458 cites W639708223 @default.
- W2804902458 doi "https://doi.org/10.1109/lgrs.2018.2830403" @default.
- W2804902458 hasPublicationYear "2018" @default.
- W2804902458 type Work @default.
- W2804902458 sameAs 2804902458 @default.
- W2804902458 citedByCount "159" @default.
- W2804902458 countsByYear W28049024582018 @default.
- W2804902458 countsByYear W28049024582019 @default.
- W2804902458 countsByYear W28049024582020 @default.
- W2804902458 countsByYear W28049024582021 @default.
- W2804902458 countsByYear W28049024582022 @default.
- W2804902458 countsByYear W28049024582023 @default.
- W2804902458 crossrefType "journal-article" @default.
- W2804902458 hasAuthorship W2804902458A5039993720 @default.
- W2804902458 hasAuthorship W2804902458A5065061505 @default.
- W2804902458 hasAuthorship W2804902458A5074919292 @default.
- W2804902458 hasConcept C115961682 @default.
- W2804902458 hasConcept C153180895 @default.
- W2804902458 hasConcept C154945302 @default.
- W2804902458 hasConcept C159078339 @default.
- W2804902458 hasConcept C31972630 @default.
- W2804902458 hasConcept C41008148 @default.
- W2804902458 hasConcept C75294576 @default.
- W2804902458 hasConcept C81363708 @default.
- W2804902458 hasConceptScore W2804902458C115961682 @default.
- W2804902458 hasConceptScore W2804902458C153180895 @default.
- W2804902458 hasConceptScore W2804902458C154945302 @default.
- W2804902458 hasConceptScore W2804902458C159078339 @default.
- W2804902458 hasConceptScore W2804902458C31972630 @default.
- W2804902458 hasConceptScore W2804902458C41008148 @default.
- W2804902458 hasConceptScore W2804902458C75294576 @default.
- W2804902458 hasConceptScore W2804902458C81363708 @default.
- W2804902458 hasFunder F4320321001 @default.
- W2804902458 hasIssue "8" @default.
- W2804902458 hasLocation W28049024581 @default.
- W2804902458 hasOpenAccess W2804902458 @default.
- W2804902458 hasPrimaryLocation W28049024581 @default.
- W2804902458 hasRelatedWork W2406522397 @default.
- W2804902458 hasRelatedWork W2726121760 @default.
- W2804902458 hasRelatedWork W2781623059 @default.
- W2804902458 hasRelatedWork W2912288872 @default.
- W2804902458 hasRelatedWork W2955667634 @default.
- W2804902458 hasRelatedWork W2972973180 @default.
- W2804902458 hasRelatedWork W2980485553 @default.
- W2804902458 hasRelatedWork W3006465478 @default.
- W2804902458 hasRelatedWork W3153891452 @default.
- W2804902458 hasRelatedWork W3181316500 @default.
- W2804902458 hasVolume "15" @default.
- W2804902458 isParatext "false" @default.
- W2804902458 isRetracted "false" @default.
- W2804902458 magId "2804902458" @default.
- W2804902458 workType "article" @default.