Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200224903> ?p ?o ?g. }
- W4200224903 endingPage "5152" @default.
- W4200224903 startingPage "5152" @default.
- W4200224903 abstract "Remote sensing (RS) image change detection (CD) is a critical technique of detecting land surface changes in earth observation. Deep learning (DL)-based approaches have gained popularity and have made remarkable progress in change detection. The recent advances in DL-based methods mainly focus on enhancing the feature representation ability for performance improvement. However, deeper networks incorporated with attention-based or multiscale context-based modules involve a large number of network parameters and require more inference time. In this paper, we first proposed an effective network called 3M-CDNet that requires about 3.12 M parameters for accuracy improvement. Furthermore, a lightweight variant called 1M-CDNet, which only requires about 1.26 M parameters, was proposed for computation efficiency with the limitation of computing power. 3M-CDNet and 1M-CDNet have the same backbone network architecture but different classifiers. Specifically, the application of deformable convolutions (DConv) in the lightweight backbone made the model gain a good geometric transformation modeling capacity for change detection. The two-level feature fusion strategy was applied to improve the feature representation. In addition, the classifier that has a plain design to facilitate the inference speed applied dropout regularization to improve generalization ability. Online data augmentation (DA) was also applied to alleviate overfitting during model training. Extensive experiments have been conducted on several public datasets for performance evaluation. Ablation studies have proved the effectiveness of the core components. Experiment results demonstrate that the proposed networks achieved performance improvements compared with the state-of-the-art methods. Specifically, 3M-CDNet achieved the best F1-score on two datasets, i.e., LEVIR-CD (0.9161) and Season-Varying (0.9749). Compared with existing methods, 1M-CDNet achieved a higher F1-score, i.e., LEVIR-CD (0.9118) and Season-Varying (0.9680). In addition, the runtime of 1M-CDNet is superior to most, which exhibits a better trade-off between accuracy and efficiency." @default.
- W4200224903 created "2021-12-31" @default.
- W4200224903 creator A5063698447 @default.
- W4200224903 creator A5079667048 @default.
- W4200224903 creator A5083752471 @default.
- W4200224903 date "2021-12-18" @default.
- W4200224903 modified "2023-09-30" @default.
- W4200224903 title "An Efficient Lightweight Neural Network for Remote Sensing Image Change Detection" @default.
- W4200224903 cites W1979061792 @default.
- W4200224903 cites W1998595580 @default.
- W4200224903 cites W2036798369 @default.
- W4200224903 cites W2042806874 @default.
- W4200224903 cites W2057670944 @default.
- W4200224903 cites W2144552105 @default.
- W4200224903 cites W2153864221 @default.
- W4200224903 cites W2154451793 @default.
- W4200224903 cites W2157026765 @default.
- W4200224903 cites W2167093797 @default.
- W4200224903 cites W2479519232 @default.
- W4200224903 cites W2611628885 @default.
- W4200224903 cites W2741377155 @default.
- W4200224903 cites W2767778161 @default.
- W4200224903 cites W2789944120 @default.
- W4200224903 cites W2804528682 @default.
- W4200224903 cites W2805152403 @default.
- W4200224903 cites W2884242593 @default.
- W4200224903 cites W2911445232 @default.
- W4200224903 cites W2951991161 @default.
- W4200224903 cites W2963420686 @default.
- W4200224903 cites W2966542792 @default.
- W4200224903 cites W2988020997 @default.
- W4200224903 cites W3011559544 @default.
- W4200224903 cites W3027059738 @default.
- W4200224903 cites W3027201985 @default.
- W4200224903 cites W3027225766 @default.
- W4200224903 cites W3036453075 @default.
- W4200224903 cites W3047032303 @default.
- W4200224903 cites W3099503507 @default.
- W4200224903 cites W3124502372 @default.
- W4200224903 cites W3130754787 @default.
- W4200224903 cites W3141138843 @default.
- W4200224903 cites W3142421496 @default.
- W4200224903 cites W3152083889 @default.
- W4200224903 cites W3152747703 @default.
- W4200224903 cites W3157062364 @default.
- W4200224903 cites W3186032668 @default.
- W4200224903 doi "https://doi.org/10.3390/rs13245152" @default.
- W4200224903 hasPublicationYear "2021" @default.
- W4200224903 type Work @default.
- W4200224903 citedByCount "10" @default.
- W4200224903 countsByYear W42002249032022 @default.
- W4200224903 countsByYear W42002249032023 @default.
- W4200224903 crossrefType "journal-article" @default.
- W4200224903 hasAuthorship W4200224903A5063698447 @default.
- W4200224903 hasAuthorship W4200224903A5079667048 @default.
- W4200224903 hasAuthorship W4200224903A5083752471 @default.
- W4200224903 hasBestOaLocation W42002249031 @default.
- W4200224903 hasConcept C119857082 @default.
- W4200224903 hasConcept C124101348 @default.
- W4200224903 hasConcept C138885662 @default.
- W4200224903 hasConcept C153180895 @default.
- W4200224903 hasConcept C154945302 @default.
- W4200224903 hasConcept C22019652 @default.
- W4200224903 hasConcept C2776214188 @default.
- W4200224903 hasConcept C2776401178 @default.
- W4200224903 hasConcept C41008148 @default.
- W4200224903 hasConcept C41895202 @default.
- W4200224903 hasConcept C50644808 @default.
- W4200224903 hasConcept C59404180 @default.
- W4200224903 hasConcept C95623464 @default.
- W4200224903 hasConceptScore W4200224903C119857082 @default.
- W4200224903 hasConceptScore W4200224903C124101348 @default.
- W4200224903 hasConceptScore W4200224903C138885662 @default.
- W4200224903 hasConceptScore W4200224903C153180895 @default.
- W4200224903 hasConceptScore W4200224903C154945302 @default.
- W4200224903 hasConceptScore W4200224903C22019652 @default.
- W4200224903 hasConceptScore W4200224903C2776214188 @default.
- W4200224903 hasConceptScore W4200224903C2776401178 @default.
- W4200224903 hasConceptScore W4200224903C41008148 @default.
- W4200224903 hasConceptScore W4200224903C41895202 @default.
- W4200224903 hasConceptScore W4200224903C50644808 @default.
- W4200224903 hasConceptScore W4200224903C59404180 @default.
- W4200224903 hasConceptScore W4200224903C95623464 @default.
- W4200224903 hasFunder F4320321001 @default.
- W4200224903 hasIssue "24" @default.
- W4200224903 hasLocation W42002249031 @default.
- W4200224903 hasLocation W42002249032 @default.
- W4200224903 hasOpenAccess W4200224903 @default.
- W4200224903 hasPrimaryLocation W42002249031 @default.
- W4200224903 hasRelatedWork W2546942002 @default.
- W4200224903 hasRelatedWork W2742991909 @default.
- W4200224903 hasRelatedWork W2753840555 @default.
- W4200224903 hasRelatedWork W2767651786 @default.
- W4200224903 hasRelatedWork W2795435272 @default.
- W4200224903 hasRelatedWork W2951851447 @default.
- W4200224903 hasRelatedWork W2970216048 @default.
- W4200224903 hasRelatedWork W2989932438 @default.
- W4200224903 hasRelatedWork W3099765033 @default.