DE-CFFN modifies an existing dual-stream CFFN architecture with Factor Analysis dimensionality reduction and halved 3D convolution filters plus an SE block to match original accuracy at lower complexity on Pavia University and Salinas datasets.
A simplified 2D-3D CNN architecture for hyperspectral image classification based on Spatial–Spectral fusion , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data Efficient Complex Feature Fusion Network For Hyperspectral Image Classification
DE-CFFN modifies an existing dual-stream CFFN architecture with Factor Analysis dimensionality reduction and halved 3D convolution filters plus an SE block to match original accuracy at lower complexity on Pavia University and Salinas datasets.