Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383315986> ?p ?o ?g. }
- W4383315986 endingPage "104796" @default.
- W4383315986 startingPage "104796" @default.
- W4383315986 abstract "Infrared images contain salient target information and visible images contain texture information. The fusion of infrared and visible images makes images express better visual understanding. Further improvement in this area is obtained by the application of the Generative Adversarial Network (GAN). But some fusion results based on GAN will lose details from the source images. Besides, sometimes the fusion results are inclined to certain source images. To force the fusion results to retain more source features and balance the information from source images, a novel GAN called multiscale feature-attention generative adversarial network (MFAGAN) is proposed. First, the infrared and visible source images are decomposed into images at different scales. Then, the multiscale images are encoded and fused at the corresponding scale. Finally, the decoder generates fused images. The game between the generator and discriminator can make the information distribution of the fusion results more reasonable, but we further propose a new generator loss function called feature-attention loss. Feature-attention loss creates a criterion that measures the similarity of high-dimensional features between fused images and source images at each scale. Extensive experiments performed on two commonly used datasets show that MFAGAN obtains good results and has some superiority over other existing methods." @default.
- W4383315986 created "2023-07-07" @default.
- W4383315986 creator A5017367838 @default.
- W4383315986 creator A5023619676 @default.
- W4383315986 creator A5038269161 @default.
- W4383315986 creator A5038552804 @default.
- W4383315986 creator A5039908048 @default.
- W4383315986 creator A5075569212 @default.
- W4383315986 date "2023-09-01" @default.
- W4383315986 modified "2023-10-11" @default.
- W4383315986 title "MFAGAN: A multiscale feature-attention generative adversarial network for infrared and visible image fusion" @default.
- W4383315986 cites W1708141795 @default.
- W4383315986 cites W2054273865 @default.
- W4383315986 cites W2081195086 @default.
- W4383315986 cites W2735436330 @default.
- W4383315986 cites W2766065559 @default.
- W4383315986 cites W2809795042 @default.
- W4383315986 cites W2912147220 @default.
- W4383315986 cites W2950648852 @default.
- W4383315986 cites W2963446712 @default.
- W4383315986 cites W2963470893 @default.
- W4383315986 cites W3003727719 @default.
- W4383315986 cites W3007891240 @default.
- W4383315986 cites W3011768656 @default.
- W4383315986 cites W3030921250 @default.
- W4383315986 cites W3096831136 @default.
- W4383315986 cites W3110902296 @default.
- W4383315986 cites W3121751387 @default.
- W4383315986 cites W3126855404 @default.
- W4383315986 cites W3139244260 @default.
- W4383315986 cites W3143068962 @default.
- W4383315986 cites W3158415971 @default.
- W4383315986 cites W3159235206 @default.
- W4383315986 cites W3199372459 @default.
- W4383315986 cites W3203672288 @default.
- W4383315986 cites W3208126581 @default.
- W4383315986 cites W4206906776 @default.
- W4383315986 cites W4221052885 @default.
- W4383315986 cites W4226178544 @default.
- W4383315986 cites W4285005614 @default.
- W4383315986 cites W4313555022 @default.
- W4383315986 doi "https://doi.org/10.1016/j.infrared.2023.104796" @default.
- W4383315986 hasPublicationYear "2023" @default.
- W4383315986 type Work @default.
- W4383315986 citedByCount "0" @default.
- W4383315986 crossrefType "journal-article" @default.
- W4383315986 hasAuthorship W4383315986A5017367838 @default.
- W4383315986 hasAuthorship W4383315986A5023619676 @default.
- W4383315986 hasAuthorship W4383315986A5038269161 @default.
- W4383315986 hasAuthorship W4383315986A5038552804 @default.
- W4383315986 hasAuthorship W4383315986A5039908048 @default.
- W4383315986 hasAuthorship W4383315986A5075569212 @default.
- W4383315986 hasConcept C115961682 @default.
- W4383315986 hasConcept C120665830 @default.
- W4383315986 hasConcept C121332964 @default.
- W4383315986 hasConcept C138885662 @default.
- W4383315986 hasConcept C153180895 @default.
- W4383315986 hasConcept C154945302 @default.
- W4383315986 hasConcept C158355884 @default.
- W4383315986 hasConcept C158525013 @default.
- W4383315986 hasConcept C163258240 @default.
- W4383315986 hasConcept C2776401178 @default.
- W4383315986 hasConcept C2778971668 @default.
- W4383315986 hasConcept C2779803651 @default.
- W4383315986 hasConcept C2780719617 @default.
- W4383315986 hasConcept C2780992000 @default.
- W4383315986 hasConcept C2988773926 @default.
- W4383315986 hasConcept C31972630 @default.
- W4383315986 hasConcept C41008148 @default.
- W4383315986 hasConcept C41895202 @default.
- W4383315986 hasConcept C62520636 @default.
- W4383315986 hasConcept C69744172 @default.
- W4383315986 hasConcept C76155785 @default.
- W4383315986 hasConcept C94915269 @default.
- W4383315986 hasConceptScore W4383315986C115961682 @default.
- W4383315986 hasConceptScore W4383315986C120665830 @default.
- W4383315986 hasConceptScore W4383315986C121332964 @default.
- W4383315986 hasConceptScore W4383315986C138885662 @default.
- W4383315986 hasConceptScore W4383315986C153180895 @default.
- W4383315986 hasConceptScore W4383315986C154945302 @default.
- W4383315986 hasConceptScore W4383315986C158355884 @default.
- W4383315986 hasConceptScore W4383315986C158525013 @default.
- W4383315986 hasConceptScore W4383315986C163258240 @default.
- W4383315986 hasConceptScore W4383315986C2776401178 @default.
- W4383315986 hasConceptScore W4383315986C2778971668 @default.
- W4383315986 hasConceptScore W4383315986C2779803651 @default.
- W4383315986 hasConceptScore W4383315986C2780719617 @default.
- W4383315986 hasConceptScore W4383315986C2780992000 @default.
- W4383315986 hasConceptScore W4383315986C2988773926 @default.
- W4383315986 hasConceptScore W4383315986C31972630 @default.
- W4383315986 hasConceptScore W4383315986C41008148 @default.
- W4383315986 hasConceptScore W4383315986C41895202 @default.
- W4383315986 hasConceptScore W4383315986C62520636 @default.
- W4383315986 hasConceptScore W4383315986C69744172 @default.
- W4383315986 hasConceptScore W4383315986C76155785 @default.
- W4383315986 hasConceptScore W4383315986C94915269 @default.
- W4383315986 hasLocation W43833159861 @default.
- W4383315986 hasOpenAccess W4383315986 @default.