An Approach Based on Low Resolution Land-Cover-Maps and Domain Adaptation to Define Representative Training Sets at Large Scale.
Iwona PodsiadloClaudia ParisLorenzo BruzzonePublished in: IGARSS (2021)
Keyphrases
- low resolution
- domain adaptation
- land cover
- high resolution
- remote sensing
- satellite images
- super resolution
- training set
- multispectral
- change detection
- remote sensing images
- semi supervised
- supervised classification
- cross domain
- supervised learning
- multiple sources
- labeled data
- high quality
- semi supervised learning
- unlabeled data
- test data
- face images
- training data
- image processing
- training examples
- geographic information systems
- target domain
- urban areas
- active learning
- pattern recognition
- image representation
- text classification
- image analysis
- object recognition
- databases
- high spatial resolution