FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328108583> ?p ?o ?g. }

• W4328108583 endingPage "394" @default.
• W4328108583 startingPage "379" @default.
• W4328108583 abstract "Recent developments in Convolutional Neural Networks (CNNs) have made them one of the most powerful image dehazing methods. In particular, the Residual Networks (ResNets), which can avoid the vanishing gradient problem effectively, are widely deployed. To understand the success of ResNets, recent mathematical analysis of ResNets reveals that a ResNet has a similar formulation as the Euler method in solving the Ordinary Differential Equations (ODE's). Hence, image dehazing which can be formulated as an optimal control problem in dynamical systems can be solved by a single-step optimal control method, such as the Euler method. This optimal control viewpoint provides a new perspective to address the problem of image restoration. Motivated by the advantages of multi-step optimal control solvers in ODE's, which include better stability and efficiency than single-step solvers, e.g. Euler, we propose the Adams-based Hierarchical Feature Fusion Network (AHFFN) for image dehazing with modules inspired by a multi-step optimal control method named the Adams-Bashforth method. Firstly, we extend a multi-step Adams-Bashforth method to the corresponding Adams block, which achieves a higher accuracy than that of single-step solvers because of its more effective use of intermediate results. Then, we stack multiple Adams blocks to mimic the discrete approximation process of an optimal control in a dynamical system. To improve the results, the hierarchical features from stacked Adams blocks are fully used by combining Hierarchical Feature Fusion (HFF) and Lightweight Spatial Attention (LSA) with Adams blocks to form a new Adams module. Finally, we not only use HFF and LSA to fuse features, but also highlight important spatial information in each Adams module for estimating the clear image. The experimental results using synthetic and real images demonstrate that the proposed AHFFN obtains better accuracy and visual results than that of state-of-the-art methods." @default.
• W4328108583 created "2023-03-22" @default.
• W4328108583 creator A5048778510 @default.
• W4328108583 creator A5054391201 @default.
• W4328108583 creator A5068828987 @default.
• W4328108583 creator A5081300658 @default.
• W4328108583 creator A5086489308 @default.
• W4328108583 date "2023-06-01" @default.
• W4328108583 modified "2023-10-03" @default.
• W4328108583 title "Adams-based hierarchical features fusion network for image dehazing" @default.
• W4328108583 cites W2139843466 @default.
• W4328108583 cites W2147318913 @default.
• W4328108583 cites W2156936307 @default.
• W4328108583 cites W2172370984 @default.
• W4328108583 cites W2256362396 @default.
• W4328108583 cites W2304687139 @default.
• W4328108583 cites W2779176852 @default.
• W4328108583 cites W2792830341 @default.
• W4328108583 cites W2947156405 @default.
• W4328108583 cites W2948606054 @default.
• W4328108583 cites W2963152299 @default.
• W4328108583 cites W2963306157 @default.
• W4328108583 cites W2963928582 @default.
• W4328108583 cites W2969218019 @default.
• W4328108583 cites W2986969740 @default.
• W4328108583 cites W2990007814 @default.
• W4328108583 cites W2997210448 @default.
• W4328108583 cites W2998249728 @default.
• W4328108583 cites W3004101291 @default.
• W4328108583 cites W3019124755 @default.
• W4328108583 cites W3034247386 @default.
• W4328108583 cites W3034331889 @default.
• W4328108583 cites W3036625258 @default.
• W4328108583 cites W3043692043 @default.
• W4328108583 cites W3082397598 @default.
• W4328108583 cites W3133769291 @default.
• W4328108583 cites W3135542706 @default.
• W4328108583 cites W3163225208 @default.
• W4328108583 cites W3173269149 @default.
• W4328108583 cites W3173342677 @default.
• W4328108583 cites W3180034634 @default.
• W4328108583 cites W3198610423 @default.
• W4328108583 cites W4211018321 @default.
• W4328108583 doi "https://doi.org/10.1016/j.neunet.2023.03.021" @default.
• W4328108583 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37141815" @default.
• W4328108583 hasPublicationYear "2023" @default.
• W4328108583 type Work @default.
• W4328108583 citedByCount "1" @default.
• W4328108583 countsByYear W43281085832023 @default.
• W4328108583 crossrefType "journal-article" @default.
• W4328108583 hasAuthorship W4328108583A5048778510 @default.
• W4328108583 hasAuthorship W4328108583A5054391201 @default.
• W4328108583 hasAuthorship W4328108583A5068828987 @default.
• W4328108583 hasAuthorship W4328108583A5081300658 @default.
• W4328108583 hasAuthorship W4328108583A5086489308 @default.
• W4328108583 hasConcept C11413529 @default.
• W4328108583 hasConcept C115961682 @default.
• W4328108583 hasConcept C134306372 @default.
• W4328108583 hasConcept C138885662 @default.
• W4328108583 hasConcept C154945302 @default.
• W4328108583 hasConcept C2524010 @default.
• W4328108583 hasConcept C2776401178 @default.
• W4328108583 hasConcept C2777210771 @default.
• W4328108583 hasConcept C28826006 @default.
• W4328108583 hasConcept C33923547 @default.
• W4328108583 hasConcept C34862557 @default.
• W4328108583 hasConcept C38409319 @default.
• W4328108583 hasConcept C41008148 @default.
• W4328108583 hasConcept C41895202 @default.
• W4328108583 hasConcept C50644808 @default.
• W4328108583 hasConcept C51544822 @default.
• W4328108583 hasConcept C62884695 @default.
• W4328108583 hasConcept C75380026 @default.
• W4328108583 hasConcept C768646 @default.
• W4328108583 hasConcept C78045399 @default.
• W4328108583 hasConceptScore W4328108583C11413529 @default.
• W4328108583 hasConceptScore W4328108583C115961682 @default.
• W4328108583 hasConceptScore W4328108583C134306372 @default.
• W4328108583 hasConceptScore W4328108583C138885662 @default.
• W4328108583 hasConceptScore W4328108583C154945302 @default.
• W4328108583 hasConceptScore W4328108583C2524010 @default.
• W4328108583 hasConceptScore W4328108583C2776401178 @default.
• W4328108583 hasConceptScore W4328108583C2777210771 @default.
• W4328108583 hasConceptScore W4328108583C28826006 @default.
• W4328108583 hasConceptScore W4328108583C33923547 @default.
• W4328108583 hasConceptScore W4328108583C34862557 @default.
• W4328108583 hasConceptScore W4328108583C38409319 @default.
• W4328108583 hasConceptScore W4328108583C41008148 @default.
• W4328108583 hasConceptScore W4328108583C41895202 @default.
• W4328108583 hasConceptScore W4328108583C50644808 @default.
• W4328108583 hasConceptScore W4328108583C51544822 @default.
• W4328108583 hasConceptScore W4328108583C62884695 @default.
• W4328108583 hasConceptScore W4328108583C75380026 @default.
• W4328108583 hasConceptScore W4328108583C768646 @default.
• W4328108583 hasConceptScore W4328108583C78045399 @default.
• W4328108583 hasFunder F4320321001 @default.
• W4328108583 hasLocation W43281085831 @default.
• W4328108583 hasLocation W43281085832 @default.

• next