Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379743502> ?p ?o ?g. }
- W4379743502 endingPage "5386" @default.
- W4379743502 startingPage "5374" @default.
- W4379743502 abstract "Change detection (CD) is a major topic in remote sensing research. Deep learning (DL)-based CD methods have made great progress. However, existing CD methods have difficulty in exploiting the different semantic and detailed information in deep and shallow features, which often leads to blurred target boundaries of identified changes. In addition, most CD methods based on the NestedUNet structure focus on improving accuracy, ignoring the importance of efficiency. Therefore, in this article, an adaptive fusion NestedUNet for CD (AFNUNet) is proposed. AFNUNet compresses the model parameters and computational cost by using the encoder based on the inverted bottleneck structure and the decoder based on the depthwise convolution. The correlation between the final multilevel feature maps extracted by NestedUNet is difficult to model by summation or concatenation. Therefore, an attention mechanism-based adaptive fusion module (AFM) is proposed. The AFM allows the network to adaptively select feature information from the final different layers of features extracted from NestedUNet in both channel and spatial dimensions so that the fused features capture deep rich semantic information while retaining detailed information at shallow boundaries. Finally, a loss function based on the Bray-Curtis distance is introduced for suppressing the sample imbalance problem. Extensive experiments on the WHU-CD, LEVIR-CD, and SYSU-CD datasets demonstrate that AFNUNet surpasses several state-of-the-art (SOTA) CD methods in terms of effectiveness. Moreover, the proposed AFNUNet remarkably reduces Params and FLOPs by 63% and 70% compared to other NestedUNet-based CD models." @default.
- W4379743502 created "2023-06-08" @default.
- W4379743502 creator A5043257030 @default.
- W4379743502 creator A5088672902 @default.
- W4379743502 creator A5092109577 @default.
- W4379743502 date "2023-01-01" @default.
- W4379743502 modified "2023-09-25" @default.
- W4379743502 title "Adaptive Fusion NestedUNet for Change Detection Using Optical Remote Sensing Images" @default.
- W4379743502 cites W1480172732 @default.
- W4379743502 cites W1677182931 @default.
- W4379743502 cites W1964669384 @default.
- W4379743502 cites W1978283872 @default.
- W4379743502 cites W1998595580 @default.
- W4379743502 cites W2006383776 @default.
- W4379743502 cites W2015780366 @default.
- W4379743502 cites W2029161185 @default.
- W4379743502 cites W2052524720 @default.
- W4379743502 cites W2100290662 @default.
- W4379743502 cites W2132083787 @default.
- W4379743502 cites W2154451793 @default.
- W4379743502 cites W2157026765 @default.
- W4379743502 cites W2160544350 @default.
- W4379743502 cites W2161273109 @default.
- W4379743502 cites W2194775991 @default.
- W4379743502 cites W2221448138 @default.
- W4379743502 cites W2278390009 @default.
- W4379743502 cites W2531409750 @default.
- W4379743502 cites W2741377155 @default.
- W4379743502 cites W2796796363 @default.
- W4379743502 cites W2804528682 @default.
- W4379743502 cites W2908320224 @default.
- W4379743502 cites W2908624219 @default.
- W4379743502 cites W2922509574 @default.
- W4379743502 cites W2939781831 @default.
- W4379743502 cites W2951991161 @default.
- W4379743502 cites W2962766617 @default.
- W4379743502 cites W2963163009 @default.
- W4379743502 cites W3009942016 @default.
- W4379743502 cites W3014641072 @default.
- W4379743502 cites W3027225766 @default.
- W4379743502 cites W3034552520 @default.
- W4379743502 cites W3099503507 @default.
- W4379743502 cites W3124502372 @default.
- W4379743502 cites W3130754787 @default.
- W4379743502 cites W3142599962 @default.
- W4379743502 cites W3164715703 @default.
- W4379743502 cites W3186032668 @default.
- W4379743502 cites W3205322569 @default.
- W4379743502 cites W4214601273 @default.
- W4379743502 cites W4220886523 @default.
- W4379743502 cites W4226253382 @default.
- W4379743502 cites W4285202454 @default.
- W4379743502 cites W4285214830 @default.
- W4379743502 cites W4285216347 @default.
- W4379743502 cites W4285298122 @default.
- W4379743502 cites W4296473474 @default.
- W4379743502 cites W4312549298 @default.
- W4379743502 cites W4313503080 @default.
- W4379743502 doi "https://doi.org/10.1109/jstars.2023.3283524" @default.
- W4379743502 hasPublicationYear "2023" @default.
- W4379743502 type Work @default.
- W4379743502 citedByCount "0" @default.
- W4379743502 crossrefType "journal-article" @default.
- W4379743502 hasAuthorship W4379743502A5043257030 @default.
- W4379743502 hasAuthorship W4379743502A5088672902 @default.
- W4379743502 hasAuthorship W4379743502A5092109577 @default.
- W4379743502 hasBestOaLocation W43797435021 @default.
- W4379743502 hasConcept C108583219 @default.
- W4379743502 hasConcept C111919701 @default.
- W4379743502 hasConcept C11413529 @default.
- W4379743502 hasConcept C114614502 @default.
- W4379743502 hasConcept C118505674 @default.
- W4379743502 hasConcept C120665830 @default.
- W4379743502 hasConcept C121332964 @default.
- W4379743502 hasConcept C127313418 @default.
- W4379743502 hasConcept C138885662 @default.
- W4379743502 hasConcept C149635348 @default.
- W4379743502 hasConcept C152139883 @default.
- W4379743502 hasConcept C153180895 @default.
- W4379743502 hasConcept C154945302 @default.
- W4379743502 hasConcept C158525013 @default.
- W4379743502 hasConcept C173608175 @default.
- W4379743502 hasConcept C192209626 @default.
- W4379743502 hasConcept C2776401178 @default.
- W4379743502 hasConcept C2780513914 @default.
- W4379743502 hasConcept C33923547 @default.
- W4379743502 hasConcept C3826847 @default.
- W4379743502 hasConcept C41008148 @default.
- W4379743502 hasConcept C41895202 @default.
- W4379743502 hasConcept C45347329 @default.
- W4379743502 hasConcept C50644808 @default.
- W4379743502 hasConcept C60008888 @default.
- W4379743502 hasConcept C62649853 @default.
- W4379743502 hasConcept C81363708 @default.
- W4379743502 hasConcept C87619178 @default.
- W4379743502 hasConceptScore W4379743502C108583219 @default.
- W4379743502 hasConceptScore W4379743502C111919701 @default.
- W4379743502 hasConceptScore W4379743502C11413529 @default.