2023
DOI: 10.1109/lgrs.2023.3244758
|View full text |Cite
|
Sign up to set email alerts
|

Local–Global Active Learning Based on a Graph Convolutional Network for Semi-Supervised Classification of Hyperspectral Imagery

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
2
1

Relationship

0
5

Authors

Journals

citations
Cited by 10 publications
(1 citation statement)
references
References 14 publications
0
1
0
Order By: Relevance
“…Conversely, the pseudo-labeling approach leverages, such as CVA or multilayer cascade screening [36] to leverage unlabeled samples. This strategic approach empowers deep learning models, including the utilization of graph neural networks [37], to be trained on a combination of real-labeled and pseudo-labeled training samples, effectively addressing the challenge posed by the limited availability of labeled data [38]. This strategic fusion optimally harnesses the strengths of both labeled and unlabeled data, resulting in a substantial enhancement in the accuracy of change detection algorithms.…”
Section: A Semi-supervised Learningmentioning
confidence: 99%
“…Conversely, the pseudo-labeling approach leverages, such as CVA or multilayer cascade screening [36] to leverage unlabeled samples. This strategic approach empowers deep learning models, including the utilization of graph neural networks [37], to be trained on a combination of real-labeled and pseudo-labeled training samples, effectively addressing the challenge posed by the limited availability of labeled data [38]. This strategic fusion optimally harnesses the strengths of both labeled and unlabeled data, resulting in a substantial enhancement in the accuracy of change detection algorithms.…”
Section: A Semi-supervised Learningmentioning
confidence: 99%