FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100826601> ?p ?o ?g. }

• W3100826601 endingPage "5626" @default.
• W3100826601 startingPage "5612" @default.
• W3100826601 abstract "Deep learning techniques have provided significant improvements in hyperspectral image (HSI) classification. The current deep learning-based HSI classifiers follow a patch-based learning framework by dividing the image into overlapping patches. As such, these methods are local learning methods, which have a high computational cost. In this article, a fast patch-free global learning (FPGA) framework is proposed for HSI classification. The proposed framework consists of three main parts: 1) a designed sampling strategy; 2) an encoder-decoder-based fully convolutional network (FCN); and 3) lateral connections between the encoder and decoder. In FPGA, an encoder-decoder-based FCN is utilized to consider the global spatial information by processing the whole image, which results in fast inference. However, it is difficult to directly utilize the encoder-decoder-based FCN for HSI classification as it always fails to converge due to the insufficiently diverse gradients caused by the limited training samples. To solve the divergence problem and maintain the FCNs abilities of fast inference and global spatial information mining, a global stochastic stratified (GS <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> ) sampling strategy is first proposed by transforming all the training samples into a stochastic sequence of stratified samples. This strategy can obtain diverse gradients to guarantee the convergence of the FCN in the FPGA framework. For a better design of FCN architecture, FreeNet, which is a fully end-to-end network for HSI classification, is proposed to maximize the exploitation of the global spatial information and boost the performance via a spectral attention-based encoder and a lightweight decoder. A lateral connection module is also designed to connect the encoder and decoder, fusing the spatial details in the encoder and the semantic features in the decoder. The experimental results obtained using three public benchmark data sets suggest that the FPGA framework is superior to the patch-based framework in both speed and accuracy for HSI classification." @default.
• W3100826601 created "2020-11-23" @default.
• W3100826601 creator A5000877601 @default.
• W3100826601 creator A5030713988 @default.
• W3100826601 creator A5066135984 @default.
• W3100826601 creator A5075903928 @default.
• W3100826601 date "2020-08-01" @default.
• W3100826601 modified "2023-10-11" @default.
• W3100826601 title "FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification" @default.
• W3100826601 cites W1521436688 @default.
• W3100826601 cites W1903029394 @default.
• W3100826601 cites W1950365613 @default.
• W3100826601 cites W1969245801 @default.
• W3100826601 cites W1971637299 @default.
• W3100826601 cites W1990653740 @default.
• W3100826601 cites W1994616650 @default.
• W3100826601 cites W1998030734 @default.
• W3100826601 cites W2008847349 @default.
• W3100826601 cites W2016860790 @default.
• W3100826601 cites W2029316659 @default.
• W3100826601 cites W2043665634 @default.
• W3100826601 cites W2090424610 @default.
• W3100826601 cites W2114819256 @default.
• W3100826601 cites W2130627644 @default.
• W3100826601 cites W2131438174 @default.
• W3100826601 cites W2136251662 @default.
• W3100826601 cites W2150579376 @default.
• W3100826601 cites W2151665594 @default.
• W3100826601 cites W2152477088 @default.
• W3100826601 cites W2164437025 @default.
• W3100826601 cites W2194775991 @default.
• W3100826601 cites W2314785379 @default.
• W3100826601 cites W2412782625 @default.
• W3100826601 cites W2500751094 @default.
• W3100826601 cites W2519653196 @default.
• W3100826601 cites W2524214095 @default.
• W3100826601 cites W2548791488 @default.
• W3100826601 cites W2732412926 @default.
• W3100826601 cites W2752782242 @default.
• W3100826601 cites W2767651786 @default.
• W3100826601 cites W2768537477 @default.
• W3100826601 cites W2772452219 @default.
• W3100826601 cites W2784118841 @default.
• W3100826601 cites W2791006446 @default.
• W3100826601 cites W2792332881 @default.
• W3100826601 cites W2800371750 @default.
• W3100826601 cites W2804902458 @default.
• W3100826601 cites W2894165434 @default.
• W3100826601 cites W2904698365 @default.
• W3100826601 cites W2907100627 @default.
• W3100826601 cites W2912961521 @default.
• W3100826601 cites W2919115771 @default.
• W3100826601 cites W2963366243 @default.
• W3100826601 cites W2963881378 @default.
• W3100826601 cites W3100011500 @default.
• W3100826601 cites W3101640299 @default.
• W3100826601 cites W4250482878 @default.
• W3100826601 doi "https://doi.org/10.1109/tgrs.2020.2967821" @default.
• W3100826601 hasPublicationYear "2020" @default.
• W3100826601 type Work @default.
• W3100826601 sameAs 3100826601 @default.
• W3100826601 citedByCount "98" @default.
• W3100826601 countsByYear W31008266012020 @default.
• W3100826601 countsByYear W31008266012021 @default.
• W3100826601 countsByYear W31008266012022 @default.
• W3100826601 countsByYear W31008266012023 @default.
• W3100826601 crossrefType "journal-article" @default.
• W3100826601 hasAuthorship W3100826601A5000877601 @default.
• W3100826601 hasAuthorship W3100826601A5030713988 @default.
• W3100826601 hasAuthorship W3100826601A5066135984 @default.
• W3100826601 hasAuthorship W3100826601A5075903928 @default.
• W3100826601 hasBestOaLocation W31008266012 @default.
• W3100826601 hasConcept C106131492 @default.
• W3100826601 hasConcept C108583219 @default.
• W3100826601 hasConcept C111919701 @default.
• W3100826601 hasConcept C118505674 @default.
• W3100826601 hasConcept C119857082 @default.
• W3100826601 hasConcept C140779682 @default.
• W3100826601 hasConcept C153180895 @default.
• W3100826601 hasConcept C154945302 @default.
• W3100826601 hasConcept C2776214188 @default.
• W3100826601 hasConcept C31972630 @default.
• W3100826601 hasConcept C41008148 @default.
• W3100826601 hasConcept C42935608 @default.
• W3100826601 hasConcept C74296488 @default.
• W3100826601 hasConcept C81363708 @default.
• W3100826601 hasConcept C9390403 @default.
• W3100826601 hasConceptScore W3100826601C106131492 @default.
• W3100826601 hasConceptScore W3100826601C108583219 @default.
• W3100826601 hasConceptScore W3100826601C111919701 @default.
• W3100826601 hasConceptScore W3100826601C118505674 @default.
• W3100826601 hasConceptScore W3100826601C119857082 @default.
• W3100826601 hasConceptScore W3100826601C140779682 @default.
• W3100826601 hasConceptScore W3100826601C153180895 @default.
• W3100826601 hasConceptScore W3100826601C154945302 @default.
• W3100826601 hasConceptScore W3100826601C2776214188 @default.
• W3100826601 hasConceptScore W3100826601C31972630 @default.
• W3100826601 hasConceptScore W3100826601C41008148 @default.

• next