2022
DOI: 10.48550/arxiv.2204.00154
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 0 publications
0
1
0
Order By: Relevance
“…In addition to the aforementioned CNN-based models, there are also some works developed based on Generative Adversarial Networks (GAN) and Graph Convolutional Networks (GCN). For example, Liu et al propose a supervised domain adaptation framework called SDACD for cross-domain change detection, which uses GAN to perform cross-domain style transformation of images, thus effectively narrowing the domain gap in a generative manner with circular consistency constraints [41]. Noh et al propose image reconstruction loss, using only an unlabeled single image as training input and generating another by GAN.…”
Section: Related Workmentioning
confidence: 99%
“…In addition to the aforementioned CNN-based models, there are also some works developed based on Generative Adversarial Networks (GAN) and Graph Convolutional Networks (GCN). For example, Liu et al propose a supervised domain adaptation framework called SDACD for cross-domain change detection, which uses GAN to perform cross-domain style transformation of images, thus effectively narrowing the domain gap in a generative manner with circular consistency constraints [41]. Noh et al propose image reconstruction loss, using only an unlabeled single image as training input and generating another by GAN.…”
Section: Related Workmentioning
confidence: 99%