A Tucker-decomposition mapping layer that reduces spatial and spectral dimensions before a 3-D CNN achieves 98.3%, 99.5%, and 99.3% overall accuracy on Indian Pines, University of Pavia, and Salinas.
Salient band selection for hyperspectral image classification via manifold ranking,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification
A Tucker-decomposition mapping layer that reduces spatial and spectral dimensions before a 3-D CNN achieves 98.3%, 99.5%, and 99.3% overall accuracy on Indian Pines, University of Pavia, and Salinas.