Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997019934> ?p ?o ?g. }
- W2997019934 endingPage "3643" @default.
- W2997019934 startingPage "3633" @default.
- W2997019934 abstract "Generative adversarial network (GAN) has made great progress in recent natural image super-resolution tasks. The key to its success is the integration of a discriminator which is trained to classify whether the input is a real high-resolution (HR) image or a generated one. Arguably, learning a strong discriminative prior is essential for generating high-quality images. However, in remote sensing images, we discover, through extensive statistical analysis, that there are more low-frequency components than natural images, which may lead to a “discrimination-ambiguity” problem, i.e., the discriminator will become “confused” to tell whether its input is real or not when dealing with those low-frequency regions, and therefore, the quality of generated HR images may be deeply affected. To address this problem, we propose a novel GAN-based super-resolution algorithm named coupled-discriminated GANs (CDGANs) for remote sensing images. Different from the previous GAN-based super-resolution models in which their discriminator takes in a single image at one time, in our model, the discriminator is specifically designed to take in a pair of images: a generated image and its HR ground truth, to make better discrimination of the inputs. We further introduce a dual pathway network architecture, a random gate, and a coupled adversarial loss to learn better correspondence between the discriminative results and the paired inputs. Experimental results on two public data sets demonstrate that our model can obtain more accurate super-resolution results in terms of both visual appearance and local details compared with other state of the arts. Our code will be made publicly available." @default.
- W2997019934 created "2020-01-10" @default.
- W2997019934 creator A5073057695 @default.
- W2997019934 creator A5087677765 @default.
- W2997019934 creator A5088611151 @default.
- W2997019934 date "2020-05-01" @default.
- W2997019934 modified "2023-10-16" @default.
- W2997019934 title "Coupled Adversarial Training for Remote Sensing Image Super-Resolution" @default.
- W2997019934 cites W1885185971 @default.
- W2997019934 cites W1930824406 @default.
- W2997019934 cites W1980038761 @default.
- W2997019934 cites W1985806826 @default.
- W2997019934 cites W2028790650 @default.
- W2997019934 cites W2030707839 @default.
- W2997019934 cites W2073623229 @default.
- W2997019934 cites W2096919863 @default.
- W2997019934 cites W2102166818 @default.
- W2997019934 cites W2121927366 @default.
- W2997019934 cites W2194775991 @default.
- W2997019934 cites W2242218935 @default.
- W2997019934 cites W2331128040 @default.
- W2997019934 cites W2359099468 @default.
- W2997019934 cites W2442495293 @default.
- W2997019934 cites W2494274259 @default.
- W2997019934 cites W2520322935 @default.
- W2997019934 cites W2565312867 @default.
- W2997019934 cites W2603566245 @default.
- W2997019934 cites W2621121458 @default.
- W2997019934 cites W2744690378 @default.
- W2997019934 cites W2768814045 @default.
- W2997019934 cites W2769613401 @default.
- W2997019934 cites W2774112877 @default.
- W2997019934 cites W2780624730 @default.
- W2997019934 cites W2789684973 @default.
- W2997019934 cites W2810821452 @default.
- W2997019934 cites W2866634454 @default.
- W2997019934 cites W2896155169 @default.
- W2997019934 cites W2898832590 @default.
- W2997019934 cites W2901919187 @default.
- W2997019934 cites W2902168190 @default.
- W2997019934 cites W2909721765 @default.
- W2997019934 cites W2927933146 @default.
- W2997019934 cites W2962687329 @default.
- W2997019934 cites W2962785568 @default.
- W2997019934 cites W2962793481 @default.
- W2997019934 cites W2963073614 @default.
- W2997019934 cites W2963372104 @default.
- W2997019934 cites W2963470893 @default.
- W2997019934 cites W2963814095 @default.
- W2997019934 cites W2964164961 @default.
- W2997019934 cites W2976372274 @default.
- W2997019934 doi "https://doi.org/10.1109/tgrs.2019.2959020" @default.
- W2997019934 hasPublicationYear "2020" @default.
- W2997019934 type Work @default.
- W2997019934 sameAs 2997019934 @default.
- W2997019934 citedByCount "70" @default.
- W2997019934 countsByYear W29970199342020 @default.
- W2997019934 countsByYear W29970199342021 @default.
- W2997019934 countsByYear W29970199342022 @default.
- W2997019934 countsByYear W29970199342023 @default.
- W2997019934 crossrefType "journal-article" @default.
- W2997019934 hasAuthorship W2997019934A5073057695 @default.
- W2997019934 hasAuthorship W2997019934A5087677765 @default.
- W2997019934 hasAuthorship W2997019934A5088611151 @default.
- W2997019934 hasConcept C115961682 @default.
- W2997019934 hasConcept C146849305 @default.
- W2997019934 hasConcept C153180895 @default.
- W2997019934 hasConcept C154945302 @default.
- W2997019934 hasConcept C199360897 @default.
- W2997019934 hasConcept C205372480 @default.
- W2997019934 hasConcept C26517878 @default.
- W2997019934 hasConcept C2779803651 @default.
- W2997019934 hasConcept C2780522230 @default.
- W2997019934 hasConcept C31972630 @default.
- W2997019934 hasConcept C38652104 @default.
- W2997019934 hasConcept C41008148 @default.
- W2997019934 hasConcept C55020928 @default.
- W2997019934 hasConcept C76155785 @default.
- W2997019934 hasConcept C94915269 @default.
- W2997019934 hasConcept C97931131 @default.
- W2997019934 hasConceptScore W2997019934C115961682 @default.
- W2997019934 hasConceptScore W2997019934C146849305 @default.
- W2997019934 hasConceptScore W2997019934C153180895 @default.
- W2997019934 hasConceptScore W2997019934C154945302 @default.
- W2997019934 hasConceptScore W2997019934C199360897 @default.
- W2997019934 hasConceptScore W2997019934C205372480 @default.
- W2997019934 hasConceptScore W2997019934C26517878 @default.
- W2997019934 hasConceptScore W2997019934C2779803651 @default.
- W2997019934 hasConceptScore W2997019934C2780522230 @default.
- W2997019934 hasConceptScore W2997019934C31972630 @default.
- W2997019934 hasConceptScore W2997019934C38652104 @default.
- W2997019934 hasConceptScore W2997019934C41008148 @default.
- W2997019934 hasConceptScore W2997019934C55020928 @default.
- W2997019934 hasConceptScore W2997019934C76155785 @default.
- W2997019934 hasConceptScore W2997019934C94915269 @default.
- W2997019934 hasConceptScore W2997019934C97931131 @default.
- W2997019934 hasFunder F4320321001 @default.
- W2997019934 hasFunder F4320322919 @default.