Joint and Progressive Subspace Analysis (JPSA) with Spatial-Spectral Manifold Alignment for Semi-Supervised Hyperspectral Dimensionality Reduction.
Danfeng HongNaoto YokoyaJocelyn ChanussotJian XuXiao Xiang ZhuPublished in: CoRR (2020)
Keyphrases
- hyperspectral
- dimensionality reduction
- subspace learning
- spectral signatures
- semi supervised
- hyperspectral data
- hyperspectral images
- remote sensing
- random projections
- hyperspectral imagery
- infrared
- low dimensional
- multispectral
- label information
- image data
- high dimensional data
- manifold learning
- principal component analysis
- high dimensional
- lower dimensional
- linear discriminant analysis
- semi supervised learning
- data representation
- pattern recognition
- feature space
- high dimensionality
- principal components
- feature selection
- feature extraction
- labeled data
- multi view
- dimensionality reduction methods
- principal components analysis
- supervised learning
- data points
- linear subspace
- graph embedding
- euclidean distance
- dimension reduction
- learning algorithm
- unsupervised learning
- singular value decomposition
- subspace methods
- pairwise
- image classification
- image processing
- computer vision