Evaluation of the Potential of Convolutional Neural Networks and Random Forests for Multi-Class Segmentation of Sentinel-2 Imagery.
Vasileios SyrrisPaul HasenohrBlagoj DelipetrevAlexander KotsevPieter KempeneersPierre SoillePublished in: Remote. Sens. (2019)
Keyphrases
- multi class
- random forests
- convolutional neural networks
- random forest
- class probabilities
- machine learning algorithms
- support vector machine
- logistic regression
- decision trees
- object detection
- multi class classification
- base classifiers
- multi class boosting
- pairwise
- ensemble methods
- multiple instance learning
- cost sensitive
- multiscale
- multi class object detection
- multiple classes
- machine learning
- feature selection
- binary classifiers
- active learning
- image segmentation
- multi class classifier
- decision tree ensembles