Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386883183> ?p ?o ?g. }
- W4386883183 endingPage "8959" @default.
- W4386883183 startingPage "8943" @default.
- W4386883183 abstract "Detecting changes in two remote sensing images of the same region but at different times is of great significance in applications such as land management and urban planning, which also prompts the continuous development and progress of change detection technology. The current deep learning-based methods make full use of the excellent feature learning ability of deep convolution to show excellent detection performance. However, advances in remote sensing technology also mean that detected objects have higher resolution and more complex content, which is more challenging for change detection techniques. Strengthening the model's ability to learn the context of the detected remote sensing image can effectively improve the model's ability to distinguish between changing features and non-changing features, thereby achieving higher-precision detection results. In order to explore and utilize the contextual information of different levels of features as much as possible, we design a Dual-attention Cross Fusion Module (DCFM) in our method to realize the cross-learning of contextual information of different scales during the decoding process. It will be able to complementarily fuse feature content of different granularities. We also propose an Atrous Pyramid Difference Module (APDM) to efficiently capture the difference information of two refined features by exploiting receptive fields of different sizes. In addition, in order to further improve the context modeling ability of the model, we introduce a context transformer block (Cot). Different from other transformer-based self-attention methods, Cot dynamically guides the learning of the attention matrix by the contextual information of the input keys. Our method achieves F1-scores of 91.08%/91.93%/79.80% on the LEVIR-CD/WHU-CD/DSIFN-CD datasets, respectively. Extensive qualitative and quantitative experiments on these datasets validate the effectiveness of our method." @default.
- W4386883183 created "2023-09-21" @default.
- W4386883183 creator A5028836596 @default.
- W4386883183 creator A5040594393 @default.
- W4386883183 creator A5052987130 @default.
- W4386883183 date "2023-01-01" @default.
- W4386883183 modified "2023-10-13" @default.
- W4386883183 title "Dual-Attention Cross Fusion Context Network for Remote Sensing Change Detection" @default.
- W4386883183 cites W1912954554 @default.
- W4386883183 cites W1924689489 @default.
- W4386883183 cites W1990653740 @default.
- W4386883183 cites W2125283600 @default.
- W4386883183 cites W2194775991 @default.
- W4386883183 cites W2273496121 @default.
- W4386883183 cites W2511065100 @default.
- W4386883183 cites W2516616494 @default.
- W4386883183 cites W2790494398 @default.
- W4386883183 cites W2794750833 @default.
- W4386883183 cites W2896092083 @default.
- W4386883183 cites W2908320224 @default.
- W4386883183 cites W2910587630 @default.
- W4386883183 cites W2911805825 @default.
- W4386883183 cites W2911964244 @default.
- W4386883183 cites W2916838572 @default.
- W4386883183 cites W2922027847 @default.
- W4386883183 cites W2951991161 @default.
- W4386883183 cites W2981689412 @default.
- W4386883183 cites W3004423752 @default.
- W4386883183 cites W3009942016 @default.
- W4386883183 cites W3015038817 @default.
- W4386883183 cites W3017051070 @default.
- W4386883183 cites W3027201985 @default.
- W4386883183 cites W3036453075 @default.
- W4386883183 cites W3037640242 @default.
- W4386883183 cites W3099503507 @default.
- W4386883183 cites W3112495912 @default.
- W4386883183 cites W3119456559 @default.
- W4386883183 cites W3120467244 @default.
- W4386883183 cites W3176244435 @default.
- W4386883183 cites W3180355996 @default.
- W4386883183 cites W3183430956 @default.
- W4386883183 cites W3208624098 @default.
- W4386883183 cites W4213124617 @default.
- W4386883183 cites W4213256221 @default.
- W4386883183 cites W4224212608 @default.
- W4386883183 cites W4226305459 @default.
- W4386883183 cites W4285298122 @default.
- W4386883183 cites W4292348075 @default.
- W4386883183 cites W4311187275 @default.
- W4386883183 cites W4312549298 @default.
- W4386883183 cites W4366147336 @default.
- W4386883183 cites W4367663360 @default.
- W4386883183 cites W4381789302 @default.
- W4386883183 doi "https://doi.org/10.1109/jstars.2023.3317488" @default.
- W4386883183 hasPublicationYear "2023" @default.
- W4386883183 type Work @default.
- W4386883183 citedByCount "0" @default.
- W4386883183 crossrefType "journal-article" @default.
- W4386883183 hasAuthorship W4386883183A5028836596 @default.
- W4386883183 hasAuthorship W4386883183A5040594393 @default.
- W4386883183 hasAuthorship W4386883183A5052987130 @default.
- W4386883183 hasBestOaLocation W43868831831 @default.
- W4386883183 hasConcept C108583219 @default.
- W4386883183 hasConcept C111919701 @default.
- W4386883183 hasConcept C119599485 @default.
- W4386883183 hasConcept C120665830 @default.
- W4386883183 hasConcept C121332964 @default.
- W4386883183 hasConcept C127413603 @default.
- W4386883183 hasConcept C138885662 @default.
- W4386883183 hasConcept C141353440 @default.
- W4386883183 hasConcept C142575187 @default.
- W4386883183 hasConcept C151730666 @default.
- W4386883183 hasConcept C153180895 @default.
- W4386883183 hasConcept C154945302 @default.
- W4386883183 hasConcept C203595873 @default.
- W4386883183 hasConcept C2776151529 @default.
- W4386883183 hasConcept C2776401178 @default.
- W4386883183 hasConcept C2779343474 @default.
- W4386883183 hasConcept C31972630 @default.
- W4386883183 hasConcept C41008148 @default.
- W4386883183 hasConcept C41895202 @default.
- W4386883183 hasConcept C52622490 @default.
- W4386883183 hasConcept C57273362 @default.
- W4386883183 hasConcept C76155785 @default.
- W4386883183 hasConcept C86803240 @default.
- W4386883183 hasConcept C98045186 @default.
- W4386883183 hasConceptScore W4386883183C108583219 @default.
- W4386883183 hasConceptScore W4386883183C111919701 @default.
- W4386883183 hasConceptScore W4386883183C119599485 @default.
- W4386883183 hasConceptScore W4386883183C120665830 @default.
- W4386883183 hasConceptScore W4386883183C121332964 @default.
- W4386883183 hasConceptScore W4386883183C127413603 @default.
- W4386883183 hasConceptScore W4386883183C138885662 @default.
- W4386883183 hasConceptScore W4386883183C141353440 @default.
- W4386883183 hasConceptScore W4386883183C142575187 @default.
- W4386883183 hasConceptScore W4386883183C151730666 @default.
- W4386883183 hasConceptScore W4386883183C153180895 @default.
- W4386883183 hasConceptScore W4386883183C154945302 @default.