A label noise tolerant random forest for the classification of remote sensing data based on outdated maps for training.
Alina E. MaasFranz RottensteinerChristian HeipkePublished in: Comput. Vis. Image Underst. (2019)
Keyphrases
- random forest
- noise tolerant
- remote sensing data
- decision trees
- feature set
- multi label
- random forests
- training set
- class labels
- classification accuracy
- training samples
- multispectral
- supervised learning
- ensemble classifier
- feature selection
- classification models
- pattern recognition
- image classification
- feature extraction
- remote sensing
- ensemble methods
- support vector
- machine learning
- noisy data
- model selection
- text classification
- feature vectors
- classification algorithm
- machine learning methods
- feature space
- hyperspectral images
- active learning
- image analysis
- generalization error
- remote sensing images
- training data
- similarity measure
- computer vision