Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045761> ?p ?o ?g. }
- W4288045761 endingPage "318" @default.
- W4288045761 startingPage "305" @default.
- W4288045761 abstract "In this paper, we propose a novel unsupervised continual-learning generative adversarial network for unified image fusion, termed as UIFGAN. In our model, for multiple image fusion tasks, a generative adversarial network for training a single model with memory in a continual-learning manner is proposed, rather than training an individual model for each fusion task or jointly training multiple tasks. We use elastic weight consolidation to avoid forgetting what has been learned from previous tasks when training multiple tasks sequentially. In each task, the generation of the fused image comes from the adversarial learning between a generator and a discriminator. Meanwhile, a max-gradient loss function is adopted for forcing the fused image to obtain richer texture details of the corresponding regions in two source images, which applies to most typical image fusion tasks. Extensive experiments on multi-exposure, multi-modal and multi-focus image fusion tasks demonstrate the advantages of our method over the state-of-the-art approaches." @default.
- W4288045761 created "2022-07-27" @default.
- W4288045761 creator A5002618865 @default.
- W4288045761 creator A5002872664 @default.
- W4288045761 creator A5021381864 @default.
- W4288045761 creator A5034184616 @default.
- W4288045761 creator A5040010053 @default.
- W4288045761 creator A5046043407 @default.
- W4288045761 creator A5064484690 @default.
- W4288045761 date "2022-12-01" @default.
- W4288045761 modified "2023-10-17" @default.
- W4288045761 title "UIFGAN: An unsupervised continual-learning generative adversarial network for unified image fusion" @default.
- W4288045761 cites W1708141795 @default.
- W4288045761 cites W1965739998 @default.
- W4288045761 cites W2054273865 @default.
- W4288045761 cites W2085518012 @default.
- W4288045761 cites W2091484864 @default.
- W4288045761 cites W2123111982 @default.
- W4288045761 cites W2133665775 @default.
- W4288045761 cites W2153777140 @default.
- W4288045761 cites W2266694576 @default.
- W4288045761 cites W2401932923 @default.
- W4288045761 cites W2522703671 @default.
- W4288045761 cites W2559870345 @default.
- W4288045761 cites W2560647685 @default.
- W4288045761 cites W2589361588 @default.
- W4288045761 cites W2590560192 @default.
- W4288045761 cites W2624240493 @default.
- W4288045761 cites W2761780228 @default.
- W4288045761 cites W2783573276 @default.
- W4288045761 cites W2788685622 @default.
- W4288045761 cites W2809795042 @default.
- W4288045761 cites W2890263162 @default.
- W4288045761 cites W2898542970 @default.
- W4288045761 cites W2905307044 @default.
- W4288045761 cites W2912147220 @default.
- W4288045761 cites W2963530785 @default.
- W4288045761 cites W2963787388 @default.
- W4288045761 cites W2964268978 @default.
- W4288045761 cites W2972566450 @default.
- W4288045761 cites W2997117931 @default.
- W4288045761 cites W2998012573 @default.
- W4288045761 cites W2998529071 @default.
- W4288045761 cites W3011768656 @default.
- W4288045761 cites W3037715783 @default.
- W4288045761 cites W3049448471 @default.
- W4288045761 cites W3105639468 @default.
- W4288045761 cites W3172595589 @default.
- W4288045761 cites W3181367324 @default.
- W4288045761 cites W3190808861 @default.
- W4288045761 cites W4206713196 @default.
- W4288045761 cites W4226178544 @default.
- W4288045761 cites W4283732315 @default.
- W4288045761 doi "https://doi.org/10.1016/j.inffus.2022.07.013" @default.
- W4288045761 hasPublicationYear "2022" @default.
- W4288045761 type Work @default.
- W4288045761 citedByCount "13" @default.
- W4288045761 countsByYear W42880457612022 @default.
- W4288045761 countsByYear W42880457612023 @default.
- W4288045761 crossrefType "journal-article" @default.
- W4288045761 hasAuthorship W4288045761A5002618865 @default.
- W4288045761 hasAuthorship W4288045761A5002872664 @default.
- W4288045761 hasAuthorship W4288045761A5021381864 @default.
- W4288045761 hasAuthorship W4288045761A5034184616 @default.
- W4288045761 hasAuthorship W4288045761A5040010053 @default.
- W4288045761 hasAuthorship W4288045761A5046043407 @default.
- W4288045761 hasAuthorship W4288045761A5064484690 @default.
- W4288045761 hasConcept C115961682 @default.
- W4288045761 hasConcept C119857082 @default.
- W4288045761 hasConcept C120665830 @default.
- W4288045761 hasConcept C121332964 @default.
- W4288045761 hasConcept C138885662 @default.
- W4288045761 hasConcept C153180895 @default.
- W4288045761 hasConcept C154945302 @default.
- W4288045761 hasConcept C162324750 @default.
- W4288045761 hasConcept C163258240 @default.
- W4288045761 hasConcept C187736073 @default.
- W4288045761 hasConcept C192209626 @default.
- W4288045761 hasConcept C2779803651 @default.
- W4288045761 hasConcept C2780451532 @default.
- W4288045761 hasConcept C2780992000 @default.
- W4288045761 hasConcept C37736160 @default.
- W4288045761 hasConcept C39890363 @default.
- W4288045761 hasConcept C41008148 @default.
- W4288045761 hasConcept C41895202 @default.
- W4288045761 hasConcept C62520636 @default.
- W4288045761 hasConcept C69744172 @default.
- W4288045761 hasConcept C7149132 @default.
- W4288045761 hasConcept C76155785 @default.
- W4288045761 hasConcept C94915269 @default.
- W4288045761 hasConceptScore W4288045761C115961682 @default.
- W4288045761 hasConceptScore W4288045761C119857082 @default.
- W4288045761 hasConceptScore W4288045761C120665830 @default.
- W4288045761 hasConceptScore W4288045761C121332964 @default.
- W4288045761 hasConceptScore W4288045761C138885662 @default.
- W4288045761 hasConceptScore W4288045761C153180895 @default.
- W4288045761 hasConceptScore W4288045761C154945302 @default.
- W4288045761 hasConceptScore W4288045761C162324750 @default.