Ensemble CNN Based on Pixel-Pair and Random Feature Selection for Hyperspectral Image Classification with Small-Size Training Set.
Shuxian DongYinghui QuanWei FengQiang LiGabriel DauphinMengdao XingPublished in: IGARSS (2021)
Keyphrases
- ensemble classifier
- small size
- training set
- hyperspectral image classification
- base classifiers
- feature selection
- active learning
- support vector machine
- ensemble learning
- weak classifiers
- decision trees
- hyperspectral
- classification accuracy
- feature space
- training data
- hyperspectral images
- training samples
- supervised learning
- cellular neural networks
- nearest neighbor
- support vector
- mutual information
- machine learning
- cross validation
- data sets
- neural network
- high dimensionality
- feature set
- feature vectors
- dimension reduction
- feature subset
- naive bayes
- random sampling
- dimensionality reduction
- principal component analysis
- image data
- high dimensional
- image processing