Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385202493> ?p ?o ?g. }
- W4385202493 endingPage "3644" @default.
- W4385202493 startingPage "3644" @default.
- W4385202493 abstract "Hyperspectral imagery (HSI) with high spectral resolution contributes to better material discrimination, while the spatial resolution limited by the sensor technique prevents it from accurately distinguishing and analyzing targets. Though generative adversarial network-based HSI super-resolution methods have achieved remarkable progress, the problems of treating vital and unessential features equally in feature expression and training instability still exist. To address these issues, an attention-enhanced generative adversarial network (AEGAN) for HSI spatial super-resolution is proposed, which elaborately designs the enhanced spatial attention module (ESAM) and refined spectral attention module (RSAM) in the attention-enhanced generator. Specifically, the devised ESAM equipped with residual spatial attention blocks (RSABs) facilitates the generator that is more focused on the spatial parts of HSI that are difficult to produce and recover, and RSAM with spectral attention refines spectral interdependencies and guarantees the spectral consistency at the respective pixel positions. Additionally, an especial U-Net discriminator with spectral normalization is enclosed to pay more attention to the detailed informations of HSI and yield to stabilize the training. For producing more realistic and detailed super-resolved HSIs, an attention-enhanced generative loss is constructed to train and constrain the AEGAN model and investigate the high correlation of spatial context and spectral information in HSI. Moreover, to better simulate the complicated and authentic degradation, pseudo-real data are also generated with a high-order degradation model to train the overall network. Experiments on three benchmark HSI datasets illustrate the superior performance of the proposed AEGAN method in HSI spatial super-resolution over the compared methods." @default.
- W4385202493 created "2023-07-25" @default.
- W4385202493 creator A5010451532 @default.
- W4385202493 creator A5040328543 @default.
- W4385202493 creator A5057854163 @default.
- W4385202493 creator A5067207818 @default.
- W4385202493 creator A5068434646 @default.
- W4385202493 date "2023-07-21" @default.
- W4385202493 modified "2023-10-16" @default.
- W4385202493 title "Attention-Enhanced Generative Adversarial Network for Hyperspectral Imagery Spatial Super-Resolution" @default.
- W4385202493 cites W1677182931 @default.
- W4385202493 cites W2010981316 @default.
- W4385202493 cites W2087380704 @default.
- W4385202493 cites W2102821790 @default.
- W4385202493 cites W2126740276 @default.
- W4385202493 cites W2144151128 @default.
- W4385202493 cites W2149760002 @default.
- W4385202493 cites W2150081556 @default.
- W4385202493 cites W2172128189 @default.
- W4385202493 cites W2194775991 @default.
- W4385202493 cites W2242218935 @default.
- W4385202493 cites W2395103039 @default.
- W4385202493 cites W2476548250 @default.
- W4385202493 cites W2503339013 @default.
- W4385202493 cites W2588000623 @default.
- W4385202493 cites W2752716059 @default.
- W4385202493 cites W2752782242 @default.
- W4385202493 cites W2767522909 @default.
- W4385202493 cites W2780544323 @default.
- W4385202493 cites W2884585870 @default.
- W4385202493 cites W2901084634 @default.
- W4385202493 cites W2955111813 @default.
- W4385202493 cites W2963372104 @default.
- W4385202493 cites W2963470893 @default.
- W4385202493 cites W2964101377 @default.
- W4385202493 cites W2971690561 @default.
- W4385202493 cites W2972330968 @default.
- W4385202493 cites W2979880570 @default.
- W4385202493 cites W2991327923 @default.
- W4385202493 cites W2997011911 @default.
- W4385202493 cites W3000573080 @default.
- W4385202493 cites W3009027729 @default.
- W4385202493 cites W3016410830 @default.
- W4385202493 cites W3023341321 @default.
- W4385202493 cites W3033214016 @default.
- W4385202493 cites W3035687950 @default.
- W4385202493 cites W3102745911 @default.
- W4385202493 cites W3109953061 @default.
- W4385202493 cites W3123265576 @default.
- W4385202493 cites W3124196789 @default.
- W4385202493 cites W3136101383 @default.
- W4385202493 cites W3198382817 @default.
- W4385202493 cites W3203631022 @default.
- W4385202493 cites W3204971388 @default.
- W4385202493 cites W4383890157 @default.
- W4385202493 cites W54257720 @default.
- W4385202493 doi "https://doi.org/10.3390/rs15143644" @default.
- W4385202493 hasPublicationYear "2023" @default.
- W4385202493 type Work @default.
- W4385202493 citedByCount "0" @default.
- W4385202493 crossrefType "journal-article" @default.
- W4385202493 hasAuthorship W4385202493A5010451532 @default.
- W4385202493 hasAuthorship W4385202493A5040328543 @default.
- W4385202493 hasAuthorship W4385202493A5057854163 @default.
- W4385202493 hasAuthorship W4385202493A5067207818 @default.
- W4385202493 hasAuthorship W4385202493A5068434646 @default.
- W4385202493 hasBestOaLocation W43852024931 @default.
- W4385202493 hasConcept C127313418 @default.
- W4385202493 hasConcept C151730666 @default.
- W4385202493 hasConcept C153180895 @default.
- W4385202493 hasConcept C154945302 @default.
- W4385202493 hasConcept C159078339 @default.
- W4385202493 hasConcept C2779343474 @default.
- W4385202493 hasConcept C2779803651 @default.
- W4385202493 hasConcept C41008148 @default.
- W4385202493 hasConcept C64754055 @default.
- W4385202493 hasConcept C76155785 @default.
- W4385202493 hasConcept C94915269 @default.
- W4385202493 hasConceptScore W4385202493C127313418 @default.
- W4385202493 hasConceptScore W4385202493C151730666 @default.
- W4385202493 hasConceptScore W4385202493C153180895 @default.
- W4385202493 hasConceptScore W4385202493C154945302 @default.
- W4385202493 hasConceptScore W4385202493C159078339 @default.
- W4385202493 hasConceptScore W4385202493C2779343474 @default.
- W4385202493 hasConceptScore W4385202493C2779803651 @default.
- W4385202493 hasConceptScore W4385202493C41008148 @default.
- W4385202493 hasConceptScore W4385202493C64754055 @default.
- W4385202493 hasConceptScore W4385202493C76155785 @default.
- W4385202493 hasConceptScore W4385202493C94915269 @default.
- W4385202493 hasFunder F4320321001 @default.
- W4385202493 hasIssue "14" @default.
- W4385202493 hasLocation W43852024931 @default.
- W4385202493 hasOpenAccess W4385202493 @default.
- W4385202493 hasPrimaryLocation W43852024931 @default.
- W4385202493 hasRelatedWork W1869808405 @default.
- W4385202493 hasRelatedWork W2028628118 @default.
- W4385202493 hasRelatedWork W2766146978 @default.
- W4385202493 hasRelatedWork W2775464024 @default.