FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133700567> ?p ?o ?g. }

• W3133700567 endingPage "86" @default.
• W3133700567 startingPage "72" @default.
• W3133700567 abstract "In the image fusion field, the design of deep learning-based fusion methods is far from routine. It is invariably fusion-task specific and requires a careful consideration. The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand. Thus, devising learnable fusion strategy is a very challenging problem in the community of image fusion. To address this problem, a novel end-to-end fusion network architecture (RFN-Nest) is developed for infrared and visible image fusion. We propose a residual fusion network (RFN) which is based on a residual architecture to replace the traditional fusion approach. A novel detail-preserving loss function, and a feature enhancing loss function are proposed to train RFN. The fusion model learning is accomplished by a novel two-stage training strategy. In the first stage, we train an auto-encoder based on an innovative nest connection (Nest) concept. Next, the RFN is trained using the proposed loss functions. The experimental results on public domain data sets show that, compared with the existing methods, our end-to-end fusion network delivers a better performance than the state-of-the-art methods in both subjective and objective evaluation. The code of our fusion method is available at https://github.com/hli1221/imagefusion-rfn-nest . • Residual fusion network (RFN) is proposed to supersede handcrafted fusion strategies. • Two-stage training strategy is developed to train RFN. • Detail preservation and feature enhancement loss functions are designed. • The proposed method achieves better performance compare with existing methods." @default.
• W3133700567 created "2021-03-15" @default.
• W3133700567 creator A5028209738 @default.
• W3133700567 creator A5064149604 @default.
• W3133700567 creator A5087450445 @default.
• W3133700567 date "2021-09-01" @default.
• W3133700567 modified "2023-10-13" @default.
• W3133700567 title "RFN-Nest: An end-to-end residual fusion network for infrared and visible images" @default.
• W3133700567 cites W1563797521 @default.
• W3133700567 cites W1580436348 @default.
• W3133700567 cites W1708141795 @default.
• W3133700567 cites W1910108985 @default.
• W3133700567 cites W1964641132 @default.
• W3133700567 cites W1965606870 @default.
• W3133700567 cites W1997201895 @default.
• W3133700567 cites W2014886478 @default.
• W3133700567 cites W2029648776 @default.
• W3133700567 cites W2040833130 @default.
• W3133700567 cites W2056346283 @default.
• W3133700567 cites W2116702374 @default.
• W3133700567 cites W2129812935 @default.
• W3133700567 cites W2133665775 @default.
• W3133700567 cites W2194775991 @default.
• W3133700567 cites W2266694576 @default.
• W3133700567 cites W2474462684 @default.
• W3133700567 cites W2527415613 @default.
• W3133700567 cites W2532801510 @default.
• W3133700567 cites W2559295071 @default.
• W3133700567 cites W2559870345 @default.
• W3133700567 cites W2606716941 @default.
• W3133700567 cites W2610070095 @default.
• W3133700567 cites W2767512561 @default.
• W3133700567 cites W2809216229 @default.
• W3133700567 cites W2809795042 @default.
• W3133700567 cites W2912147220 @default.
• W3133700567 cites W2938696568 @default.
• W3133700567 cites W2945809413 @default.
• W3133700567 cites W2963134949 @default.
• W3133700567 cites W2963446712 @default.
• W3133700567 cites W2963530785 @default.
• W3133700567 cites W2963787388 @default.
• W3133700567 cites W2963905288 @default.
• W3133700567 cites W2998012573 @default.
• W3133700567 cites W3011768656 @default.
• W3133700567 cites W3102411220 @default.
• W3133700567 cites W3105639468 @default.
• W3133700567 cites W3143068962 @default.
• W3133700567 doi "https://doi.org/10.1016/j.inffus.2021.02.023" @default.
• W3133700567 hasPublicationYear "2021" @default.
• W3133700567 type Work @default.
• W3133700567 sameAs 3133700567 @default.
• W3133700567 citedByCount "211" @default.
• W3133700567 countsByYear W31337005672021 @default.
• W3133700567 countsByYear W31337005672022 @default.
• W3133700567 countsByYear W31337005672023 @default.
• W3133700567 crossrefType "journal-article" @default.
• W3133700567 hasAuthorship W3133700567A5028209738 @default.
• W3133700567 hasAuthorship W3133700567A5064149604 @default.
• W3133700567 hasAuthorship W3133700567A5087450445 @default.
• W3133700567 hasBestOaLocation W31337005672 @default.
• W3133700567 hasConcept C108583219 @default.
• W3133700567 hasConcept C111919701 @default.
• W3133700567 hasConcept C11413529 @default.
• W3133700567 hasConcept C115961682 @default.
• W3133700567 hasConcept C118505674 @default.
• W3133700567 hasConcept C119857082 @default.
• W3133700567 hasConcept C127413603 @default.
• W3133700567 hasConcept C138885662 @default.
• W3133700567 hasConcept C14036430 @default.
• W3133700567 hasConcept C153180895 @default.
• W3133700567 hasConcept C154945302 @default.
• W3133700567 hasConcept C155512373 @default.
• W3133700567 hasConcept C158525013 @default.
• W3133700567 hasConcept C177264268 @default.
• W3133700567 hasConcept C199360897 @default.
• W3133700567 hasConcept C201995342 @default.
• W3133700567 hasConcept C2776401178 @default.
• W3133700567 hasConcept C2776760102 @default.
• W3133700567 hasConcept C2780451532 @default.
• W3133700567 hasConcept C41008148 @default.
• W3133700567 hasConcept C41895202 @default.
• W3133700567 hasConcept C69744172 @default.
• W3133700567 hasConcept C78458016 @default.
• W3133700567 hasConcept C86803240 @default.
• W3133700567 hasConceptScore W3133700567C108583219 @default.
• W3133700567 hasConceptScore W3133700567C111919701 @default.
• W3133700567 hasConceptScore W3133700567C11413529 @default.
• W3133700567 hasConceptScore W3133700567C115961682 @default.
• W3133700567 hasConceptScore W3133700567C118505674 @default.
• W3133700567 hasConceptScore W3133700567C119857082 @default.
• W3133700567 hasConceptScore W3133700567C127413603 @default.
• W3133700567 hasConceptScore W3133700567C138885662 @default.
• W3133700567 hasConceptScore W3133700567C14036430 @default.
• W3133700567 hasConceptScore W3133700567C153180895 @default.
• W3133700567 hasConceptScore W3133700567C154945302 @default.
• W3133700567 hasConceptScore W3133700567C155512373 @default.
• W3133700567 hasConceptScore W3133700567C158525013 @default.
• W3133700567 hasConceptScore W3133700567C177264268 @default.

• next