Matches in SemOpenAlex for { <https://semopenalex.org/work/W2942855565> ?p ?o ?g. }
- W2942855565 endingPage "6973" @default.
- W2942855565 startingPage "6960" @default.
- W2942855565 abstract "Supervised deep neural networks (DNNs) have been extensively used in diverse tasks. Generally, training such DNNs with superior performance requires a large amount of labeled data. However, it is time-consuming and expensive to manually label the data, especially for tasks in remote sensing, e.g., change detection. The situation motivates us to resort to the existing related images with labels, from which the concept of change can be adapted to new images. However, the distributions of the related labeled images (source domain) and unlabeled new images (target domain) are similar but not identical. It impedes a change detection model learned from source domains being well applied to the target domain. In this paper, we propose a transferred deep learning-based change detection framework to solve this problem. It consists of pretraining and fine-tuning stages. In the pretraining process, we propose two tasks to be learned simultaneously, namely, change detection for the source domain with labels and reconstruction of the unlabeled target data. The auxiliary task aims to reconstruct the difference image (DI) for the target domain. DI is an effective feature, such that the auxiliary task is of much relevance to change detection. The lower layers are shared between these two tasks in the training process. It mitigates the distribution discrepancy between the source and target domains and makes the concept of change from the source domain adapt to the target domain. In addition, we evaluate three modes of the U-net architecture to merge the information for a pair of patches. To fine-tune the change detection network (CDN) for the target domain, two strategies are exploited to select the pixels that have a high possibility of being correctly classified by an unsupervised approach. The proposed method demonstrates an excellent capacity for adapting the concept of change from the source domain to the target domain. It outperforms the state-of-the-art change detection methods via experimental results on real remote sensing data sets." @default.
- W2942855565 created "2019-05-09" @default.
- W2942855565 creator A5005190048 @default.
- W2942855565 creator A5022459300 @default.
- W2942855565 creator A5043022387 @default.
- W2942855565 creator A5050630882 @default.
- W2942855565 creator A5069606416 @default.
- W2942855565 date "2019-09-01" @default.
- W2942855565 modified "2023-10-18" @default.
- W2942855565 title "Transferred Deep Learning-Based Change Detection in Remote Sensing Images" @default.
- W2942855565 cites W1661193476 @default.
- W2942855565 cites W1964069486 @default.
- W2942855565 cites W1971580912 @default.
- W2942855565 cites W1990881969 @default.
- W2942855565 cites W1997413270 @default.
- W2942855565 cites W2003978305 @default.
- W2942855565 cites W2004307968 @default.
- W2942855565 cites W2029161185 @default.
- W2942855565 cites W2034073840 @default.
- W2942855565 cites W2049061912 @default.
- W2942855565 cites W2089947415 @default.
- W2942855565 cites W2090822373 @default.
- W2942855565 cites W2102228434 @default.
- W2942855565 cites W2104374858 @default.
- W2942855565 cites W2108262882 @default.
- W2942855565 cites W2110519070 @default.
- W2942855565 cites W2113913629 @default.
- W2942855565 cites W2118116484 @default.
- W2942855565 cites W2128117981 @default.
- W2942855565 cites W2133444763 @default.
- W2942855565 cites W2144552105 @default.
- W2942855565 cites W2160544350 @default.
- W2942855565 cites W2165350297 @default.
- W2942855565 cites W2221448138 @default.
- W2942855565 cites W2240067561 @default.
- W2942855565 cites W2261462550 @default.
- W2942855565 cites W2280565539 @default.
- W2942855565 cites W2315349446 @default.
- W2942855565 cites W2478454054 @default.
- W2942855565 cites W2531619007 @default.
- W2942855565 cites W2564658196 @default.
- W2942855565 cites W2568858292 @default.
- W2942855565 cites W2593768305 @default.
- W2942855565 cites W2627081599 @default.
- W2942855565 cites W2751993439 @default.
- W2942855565 cites W2752414286 @default.
- W2942855565 cites W2773075718 @default.
- W2942855565 cites W2774942496 @default.
- W2942855565 cites W2781778455 @default.
- W2942855565 doi "https://doi.org/10.1109/tgrs.2019.2909781" @default.
- W2942855565 hasPublicationYear "2019" @default.
- W2942855565 type Work @default.
- W2942855565 sameAs 2942855565 @default.
- W2942855565 citedByCount "69" @default.
- W2942855565 countsByYear W29428555652020 @default.
- W2942855565 countsByYear W29428555652021 @default.
- W2942855565 countsByYear W29428555652022 @default.
- W2942855565 countsByYear W29428555652023 @default.
- W2942855565 crossrefType "journal-article" @default.
- W2942855565 hasAuthorship W2942855565A5005190048 @default.
- W2942855565 hasAuthorship W2942855565A5022459300 @default.
- W2942855565 hasAuthorship W2942855565A5043022387 @default.
- W2942855565 hasAuthorship W2942855565A5050630882 @default.
- W2942855565 hasAuthorship W2942855565A5069606416 @default.
- W2942855565 hasConcept C108583219 @default.
- W2942855565 hasConcept C111919701 @default.
- W2942855565 hasConcept C134306372 @default.
- W2942855565 hasConcept C138885662 @default.
- W2942855565 hasConcept C153180895 @default.
- W2942855565 hasConcept C154945302 @default.
- W2942855565 hasConcept C158154518 @default.
- W2942855565 hasConcept C162324750 @default.
- W2942855565 hasConcept C17744445 @default.
- W2942855565 hasConcept C187736073 @default.
- W2942855565 hasConcept C197129107 @default.
- W2942855565 hasConcept C199539241 @default.
- W2942855565 hasConcept C203595873 @default.
- W2942855565 hasConcept C23123220 @default.
- W2942855565 hasConcept C2776145971 @default.
- W2942855565 hasConcept C2776401178 @default.
- W2942855565 hasConcept C2780451532 @default.
- W2942855565 hasConcept C2984842247 @default.
- W2942855565 hasConcept C31972630 @default.
- W2942855565 hasConcept C33923547 @default.
- W2942855565 hasConcept C36503486 @default.
- W2942855565 hasConcept C41008148 @default.
- W2942855565 hasConcept C41895202 @default.
- W2942855565 hasConcept C50644808 @default.
- W2942855565 hasConcept C52622490 @default.
- W2942855565 hasConcept C98045186 @default.
- W2942855565 hasConceptScore W2942855565C108583219 @default.
- W2942855565 hasConceptScore W2942855565C111919701 @default.
- W2942855565 hasConceptScore W2942855565C134306372 @default.
- W2942855565 hasConceptScore W2942855565C138885662 @default.
- W2942855565 hasConceptScore W2942855565C153180895 @default.
- W2942855565 hasConceptScore W2942855565C154945302 @default.
- W2942855565 hasConceptScore W2942855565C158154518 @default.
- W2942855565 hasConceptScore W2942855565C162324750 @default.