FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313004766> ?p ?o ?g. }

• W4313004766 endingPage "14" @default.
• W4313004766 startingPage "1" @default.
• W4313004766 abstract "Convolutional neural networks (CNNs) are widely used in hyperspectral image (HSI) classification. However, the network architecture of CNNs is often designed manually, which requires careful fine-tuning. Recently, many techniques for neural architecture search (NAS) have been proposed to design the network automatically but most of the methods are only concerned with the overall classification accuracy and ignore the balance between the floating point operations per second (FLOPs) and the number of parameters. In this paper, we propose a new multi-objective optimization (MO) method called MO-CNN to automatically design the structure of CNNs for HSI classification. First, a MO method based on continuous particle swarm optimization (CPSO) is constructed, where the overall accuracy, floating point operations (FLOPs) and the number of parameters are considered, to obtain an optimal architecture from the Pareto front. Then, an auxiliary skip connection strategy is added (together with a partial connection strategy) to avoid performance collapse and to reduce memory consumption. Furthermore, an end-to-end band selection network (BS-Net) is used to reduce redundant bands and to maintain spectral-spatial uniformity. To demonstrate the performance of our newly proposed MO-CNN in scenarios with limited training sets, a quantitative and comparative analysis (including ablation studies) is conducted. Our optimization strategy is shown to improve the classification accuracy, reduce memory and obtain an optimal structure for CNNs based on unbiased datasets." @default.
• W4313004766 created "2023-01-05" @default.
• W4313004766 creator A5038861185 @default.
• W4313004766 creator A5049699386 @default.
• W4313004766 creator A5054292278 @default.
• W4313004766 creator A5062400971 @default.
• W4313004766 creator A5078539725 @default.
• W4313004766 creator A5078908602 @default.
• W4313004766 creator A5083896582 @default.
• W4313004766 date "2022-01-01" @default.
• W4313004766 modified "2023-10-18" @default.
• W4313004766 title "MO-CNN: Multiobjective Optimization of Convolutional Neural Networks for Hyperspectral Image Classification" @default.
• W4313004766 cites W1522750079 @default.
• W4313004766 cites W2194775991 @default.
• W4313004766 cites W2796265726 @default.
• W4313004766 cites W2910688461 @default.
• W4313004766 cites W2937638900 @default.
• W4313004766 cites W2943270518 @default.
• W4313004766 cites W2954234207 @default.
• W4313004766 cites W2962770389 @default.
• W4313004766 cites W2963918968 @default.
• W4313004766 cites W2964081807 @default.
• W4313004766 cites W2964148549 @default.
• W4313004766 cites W2968300580 @default.
• W4313004766 cites W2981708954 @default.
• W4313004766 cites W3034357629 @default.
• W4313004766 cites W3041694656 @default.
• W4313004766 cites W3102274762 @default.
• W4313004766 cites W3107893198 @default.
• W4313004766 cites W3118513496 @default.
• W4313004766 cites W3128861763 @default.
• W4313004766 cites W3129613340 @default.
• W4313004766 cites W3131407372 @default.
• W4313004766 cites W3133744039 @default.
• W4313004766 cites W3136985054 @default.
• W4313004766 cites W3191251640 @default.
• W4313004766 cites W3205127501 @default.
• W4313004766 cites W3205903836 @default.
• W4313004766 cites W3209698263 @default.
• W4313004766 cites W3212336101 @default.
• W4313004766 cites W4255158661 @default.
• W4313004766 doi "https://doi.org/10.1109/tgrs.2022.3220748" @default.
• W4313004766 hasPublicationYear "2022" @default.
• W4313004766 type Work @default.
• W4313004766 citedByCount "10" @default.
• W4313004766 countsByYear W43130047662022 @default.
• W4313004766 countsByYear W43130047662023 @default.
• W4313004766 crossrefType "journal-article" @default.
• W4313004766 hasAuthorship W4313004766A5038861185 @default.
• W4313004766 hasAuthorship W4313004766A5049699386 @default.
• W4313004766 hasAuthorship W4313004766A5054292278 @default.
• W4313004766 hasAuthorship W4313004766A5062400971 @default.
• W4313004766 hasAuthorship W4313004766A5078539725 @default.
• W4313004766 hasAuthorship W4313004766A5078908602 @default.
• W4313004766 hasAuthorship W4313004766A5083896582 @default.
• W4313004766 hasConcept C11413529 @default.
• W4313004766 hasConcept C115961682 @default.
• W4313004766 hasConcept C119857082 @default.
• W4313004766 hasConcept C153180895 @default.
• W4313004766 hasConcept C154945302 @default.
• W4313004766 hasConcept C159078339 @default.
• W4313004766 hasConcept C173608175 @default.
• W4313004766 hasConcept C193415008 @default.
• W4313004766 hasConcept C3826847 @default.
• W4313004766 hasConcept C38652104 @default.
• W4313004766 hasConcept C41008148 @default.
• W4313004766 hasConcept C68781425 @default.
• W4313004766 hasConcept C75294576 @default.
• W4313004766 hasConcept C81363708 @default.
• W4313004766 hasConcept C85617194 @default.
• W4313004766 hasConceptScore W4313004766C11413529 @default.
• W4313004766 hasConceptScore W4313004766C115961682 @default.
• W4313004766 hasConceptScore W4313004766C119857082 @default.
• W4313004766 hasConceptScore W4313004766C153180895 @default.
• W4313004766 hasConceptScore W4313004766C154945302 @default.
• W4313004766 hasConceptScore W4313004766C159078339 @default.
• W4313004766 hasConceptScore W4313004766C173608175 @default.
• W4313004766 hasConceptScore W4313004766C193415008 @default.
• W4313004766 hasConceptScore W4313004766C3826847 @default.
• W4313004766 hasConceptScore W4313004766C38652104 @default.
• W4313004766 hasConceptScore W4313004766C41008148 @default.
• W4313004766 hasConceptScore W4313004766C68781425 @default.
• W4313004766 hasConceptScore W4313004766C75294576 @default.
• W4313004766 hasConceptScore W4313004766C81363708 @default.
• W4313004766 hasConceptScore W4313004766C85617194 @default.
• W4313004766 hasFunder F4320321001 @default.
• W4313004766 hasLocation W43130047661 @default.
• W4313004766 hasOpenAccess W4313004766 @default.
• W4313004766 hasPrimaryLocation W43130047661 @default.
• W4313004766 hasRelatedWork W2028628118 @default.
• W4313004766 hasRelatedWork W2767651786 @default.
• W4313004766 hasRelatedWork W2781623059 @default.
• W4313004766 hasRelatedWork W2912288872 @default.
• W4313004766 hasRelatedWork W2986507176 @default.
• W4313004766 hasRelatedWork W3005814217 @default.
• W4313004766 hasRelatedWork W3006334803 @default.
• W4313004766 hasRelatedWork W3012393889 @default.
• W4313004766 hasRelatedWork W3173596272 @default.

• next