Bi-directional LSTM with multi-scale dense attention mechanism for hyperspectral image classification

Feature representation has always been the top priority of research in the field of hyperspectral image (HSI) classification. Efficient analysis of those features extracted from HSI massively depends on the way how features are represented. In this paper, we propose a bi-directional long short-term memory network (Bi-LSTM)-based multi-scale dense attention framework, namely MBDA-Net. In this framework, we develop a new multi-scale dense attention module (MCDA) that uses different sizes of convolution kernels to obtain multi-scale features. Then, we perform feature selection by using a multi-layer attention mechanism that assigns different weight coefficients to the extracted multi-scale features. Specifically, we use the bi-directional LSTM to obtain contextual semantic information. The extensive experiments conducted on three hyperspectral datasets demonstrate the effectiveness of our method in identifying hyperspectral images.

Automated summary

In this paper, a Bi-LSTM-based multi-scale dense attention framework, MBDA-Net, is proposed for hyperspectral image classification. The framework utilizes multi-scale feature extraction and attention mechanism for feature selection, and employs bi-directional LSTM to capture contextual semantic information. Experimental results demonstrate the effectiveness of the proposed method in identifying hyperspectral images.