A 3D 2D convolutional Neural Network Model for Hyperspectral Image Classification
This work addresses hyperspectral image classification for remote sensing applications, presenting an incremental improvement in efficiency with very few labeled samples.
The paper tackles hyperspectral image classification by proposing the SEHybridSN model, which uses dense blocks, depth separable convolutional layers, and channel attention to exploit spatial-spectral features, achieving satisfactory performance with only 0.05 and 0.01 labeled data for training.
In the proposed SEHybridSN model, a dense block was used to reuse shallow feature and aimed at better exploiting hierarchical spatial spectral feature. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial spectral features was realized by the channel attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer. Experiment results indicate that our proposed model learn more discriminative spatial spectral features using very few training data. SEHybridSN using only 0.05 and 0.01 labeled data for training, a very satisfactory performance is obtained.