Shorten Spatial-spectral RNN with Parallel-GRU for Hyperspectral Image Classification
This work improves classification accuracy for hyperspectral sensing images, but it is incremental as it builds on existing RNN and CNN methods.
The authors tackled the problem of hyperspectral image classification by addressing the inefficiency of RNNs on long sequences and their lack of spatial feature consideration, proposing a Shorten Spatial-spectral RNN with Parallel-GRU (St-SS-pGRU) that achieved better performance and robustness.
Convolutional neural networks (CNNs) attained a good performance in hyperspectral sensing image (HSI) classification, but CNNs consider spectra as orderless vectors. Therefore, considering the spectra as sequences, recurrent neural networks (RNNs) have been applied in HSI classification, for RNNs is skilled at dealing with sequential data. However, for a long-sequence task, RNNs is difficult for training and not as effective as we expected. Besides, spatial contextual features are not considered in RNNs. In this study, we propose a Shorten Spatial-spectral RNN with Parallel-GRU (St-SS-pGRU) for HSI classification. A shorten RNN is more efficient and easier for training than band-by-band RNN. By combining converlusion layer, the St-SSpGRU model considers not only spectral but also spatial feature, which results in a better performance. An architecture named parallel-GRU is also proposed and applied in St-SS-pGRU. With this architecture, the model gets a better performance and is more robust.