An Investigation of a Multidimensional CNN Combined with an Attention Mechanism Model to Resolve Small-Sample Problems in Hyperspectral Image Classification

Abstract

The convolutional neural network (CNN) method has been widely used in the classification of hyperspectral images (HSIs). However, the efficiency and accuracy of the HSI classification are inevitably degraded when small samples are available. This study proposes a multidimensional CNN model named MDAN, which is constructed with an attention mechanism, to achieve an ideal classification performance of CNN within the framework of few-shot learning. In this model, a three-dimensional (3D) convolutional layer is carried out for obtaining spatial–spectral features from the 3D volumetric data of HSI. Subsequently, the two-dimensional (2D) and one-dimensional (1D) convolutional layers further learn spatial and spectral features efficiently at an abstract level. Based on the most widely used convolutional block attention module (CBAM), this study investigates a convolutional block self-attention module (CBSM) to improve accuracy by changing the connection ways of attention blocks. The CBSM model is used with the 2D convolutional layer for better performance of HSI classification purposes. The MDAN model is applied for classification applications using HSI, and its performance is evaluated by comparing the results with the support vector machine (SVM), 2D CNN, 3D CNN, 3D–2D–1D CNN, and CBAM. The findings of this study indicate that classification results from the MADN model show overall classification accuracies of 97.34%, 96.43%, and 92.23% for Salinas, WHU-Hi-HanChuan, and Pavia University datasets, respectively, when only 1% HSI data were used for training. The training and testing times of the MDAN model are close to those of the 3D–2D–1D CNN, which has the highest efficiency among all comparative CNN models. The attention model CBSM is introduced into MDAN, which achieves an overall accuracy of about 1% higher than that of the CBAM model. The performance of the two proposed methods is superior to the other models in terms of both efficiency and accuracy. The results show that the combination of multidimensional CNNs and attention mechanisms has the best ability for small-sample problems in HSI classification.

An Improved 3D-2D Convolutional Neural Network Based on Feature Optimization for Hyperspectral Image Classification

“…In order to evaluate the performance of the proposed model in the case of small samples, this section will compare and analyze the proposed method with several deep learning methods developed in recent years, which are DFFN [52], SSRN [20], MSDN [53], BAM-CM [54], HybridSN [18], MSRN-A [55], MSR-3DCNN [56], and MDAN [49]. The following is a brief introduction to each method in order of publication time.…”

“…In the study of hyperspectral image classification, there is no clear definition of small sample learning. Therefore, this paper refers to the recent research work for training sample division and experimental analysis [46], [47], [48], [49]. In addition, to ensure the effective flow of information in the propagation process, the robust neural network parameter initialization method proposed by He et al [50] is used.…”

Autonomous Detection of Spodoptera frugiperda by Feeding Symptoms Directly from UAV RGB Imagery

“…Chen et al used the UNet-based BLSNet to automatic identify and segment the diseased region of Rice bacterial leaf streak from the camera photos [24]. The appearance of the attention mechanism also further improves the performance of the network [22,25].…”

Transformer attention network and unmanned aerial vehicle hyperspectral remote sensing for grassland rodent pest monitoring research

“…At present, HSI classification and recognition methods are mainly based on two classification algorithms, machine learning and deep learning. 49 Machine learning methods require a large amount of spectral analysis and feature extraction for HSI, and the operation process is tedious and time-consuming. 50 In addition, the classification performance of machine learning is also related to the extracted features, and the human influence factor is large, so it is difficult to improve the classification performance.…”

“…At present, HSI classification and recognition methods are mainly based on two classification algorithms, machine learning and deep learning 49 . Machine learning methods require a large amount of spectral analysis and feature extraction for HSI, and the operation process is tedious and time-consuming 50 .…”