Residual Group Channel and Space Attention Network for Hyperspectral Image Classification

Abstract

Recently, deep learning methods based on three-dimensional (3-D) convolution have been widely used in the hyperspectral image (HSI) classification tasks and shown good classification performance. However, affected by the irregular distribution of various classes in HSI datasets, most previous 3-D convolutional neural network (CNN)-based models require more training samples to obtain better classification accuracies. In addition, as the network deepens, which leads to the spatial resolution of feature maps gradually decreasing, much useful information may be lost during the training process. Therefore, how to ensure efficient network training is key to the HSI classification tasks. To address the issue mentioned above, in this paper, we proposed a 3-DCNN-based residual group channel and space attention network (RGCSA) for HSI classification. Firstly, the proposed bottom-up top-down attention structure with the residual connection can improve network training efficiency by optimizing channel-wise and spatial-wise features throughout the whole training process. Secondly, the proposed residual group channel-wise attention module can reduce the possibility of losing useful information, and the novel spatial-wise attention module can extract context information to strengthen the spatial features. Furthermore, our proposed RGCSA network only needs few training samples to achieve higher classification accuracies than previous 3-D-CNN-based networks. The experimental results on three commonly used HSI datasets demonstrate the superiority of our proposed network based on the attention mechanism and the effectiveness of the proposed channel-wise and spatial-wise attention modules for HSI classification. The code and configurations are released at Github.com.

Ship Classification Based on Attention Mechanism and Multi-Scale Convolutional Neural Network for Visible and Infrared Images

“…In visual perception, it pays attention mainly to the features of interest, and suppresses redundant information. The attention mechanism can be integrated into the CNN framework with negligible overhead, and trained together with CNN [31]. Inspired by the convolutional block attention module (CBAM) [32] which allows auto-learning of pixel correlation among different feature maps, we add the attention mechanism after feature fusion layer.…”

Attention-Based Domain Adaptation Using Residual Network for Hyperspectral Image Classification

“…The Fig. 1: Block diagram of the proposed method authors use long short-term memory (LSTM) model, and a multi-scale convolutional neural network to extract spectral and spatial features, respectively, showing an improvement of overall accuracy in the case of multiple HSI datasets.For attention transfer based approaches mainly inspired from the unsupervised image saliency detection with Gestalt-laws guided optimization and attention in [31], a three dimensional convolutional neural network (3-DCNN) based residual channel and space attention network (RGSCA) is used for HSI classification [32]. It uses residual connection in both bottomup and top-down manner to optimize the attentions of the channel and spatial wise features in the training process.…”

Improved Transformer Net for Hyperspectral Image Classification

“…The models proposed in [33] and [35] converge at 50 and 100 epochs, respectively. To solve this problem, quite a few algorithms extract the spatial and spectral features separately and introduce the attention mechanism for HSI classification [36][37][38][39][40][41]. For example, Zhu et al [36] propose an end-to-end residual spectral-spatial attention network (RSSAN), which can adaptively realize the selection of spatial information and spectrum information.…”