H2A2Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification

Shi, Hao; Cao, Guo; Zhang, Youqiang; Ge, Zixian; Liu, Yanbo; Fu, Peng

doi:10.3390/rs14174235

Cited by 13 publications

(7 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…R. Shang et al [27] proposed a hyperspectral image classification approach (MCRSCA) based on multiscale cross-branching response and second-order channel attention to capture small distinctions between several categories and extract nonlocal contextual information. Additionally, to fully utilize the advantages of multiscale methods and attention mechanisms, Shi et al [28] proposed a multibranch hybrid CNN based on multiresolution and attention mechanisms to emphasize useful spectral-spatial information. Xu et al [29] suggested a multiscale and crosslevel attention learning (MCAL) network to account for both spatial context and spectral information.…”

Section: A Spectral-spatial Feature Extraction Methods In Hsi Classif...mentioning

confidence: 99%

LSSMA: Lightweight Spectral–Spatial Neural Architecture With Multiattention Feature Extraction for Hyperspectral Image Classification

Ding,

Ruan,

Yang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deep learning has been utilized for hyperspectral image (HSI) classification in recent years, with notable performance improvements. In particular, convolutional neural networks (CNNs) methods have achieved major advancements in this area. However, there are some drawbacks to the existing CNN-based HSI classification approaches: 1) the lack of effective and simple feature representations in CNNs, which overlook the effects of spectral differences and spatial contextual information; 2) the classification model has an enormous network complexity as a result of its numerous training parameters and high computational requirements; and 3) the category samples in HSI data exhibit a significant long tail distribution issue, which affects the classification performance of HSI. To address these issues, we propose a lightweight spectral-spatial neural architecture with multi-attention feature extraction (LSSMA) for HSI classification. The main work consists of three areas:1) a spectral feature extraction and fusing module (SFEF) is created to facilitate the fusing of spectral-spatial features while reducing the number of trainable parameters and computational complexity of the model. This module uses convolutions of various kernel sizes for residual connection and feature fusion, and introduces group convolution to achieve efficient feature representation; 2)to utilize the spectralspatial correlation of HSI data to its fullest, a multi-scale convolutional activation guided attention mechanism (MsCA) is designed and the position attention module (PAM) is referenced, which can capture spectral differences and spatial contextual relationships between ground objects; and 3) focal loss (FL) is applied in computer vision tasks to the LSSMA model to enhance its capacity to handle category imbalance. Experimental results on four publicly available hyperspectral datasets show that the method obtains better classification performance at a lower computational cost.

show abstract

Section: A Spectral-spatial Feature Extraction Methods In Hsi Classif...mentioning

confidence: 99%

LSSMA: Lightweight Spectral–Spatial Neural Architecture With Multiattention Feature Extraction for Hyperspectral Image Classification

Ding,

Ruan,

Yang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Relevant spatial areas are mainly composed of the pixels which have the same label as the center pixel of the sample. Features extracted from these areas generally reveal the distinctive information of each class [162,171,178]. In this section, techniques to obtain common spatial features and relevant spatial areas are outlined.…”

Section: Extraction Of Discriminating Spatial Featuresmentioning

confidence: 99%

“…Convolution-based spatial attention modules [170,173,175] usually adopt convolutional layers to connect the local correlations between regions with spatial attention. GE modules [169] utilize depth-wise convolution to gather and assess the correlations between spectral features in small regions and resize aggregated weights for adjustment [170][171][172]. To consider more useful information of input, spa-CBAMs [147] introduce global average pooling and max-pooling layers before convolution, which improve spatial attention without increasing the number of parameters [161][162][163][164][173][174][175].…”

Section: Convolution-based Spatial Attentionmentioning

confidence: 99%

“…The prototype of first pattern is the gather-and-excitation (GE) module [169]. It can gather spectral semantic representation within small regions and search for the responses between local representation and relevant areas [170][171][172]. Based on the GE module, the spatial part of CBAM (spa-CBAM) [147] introduced global max-pooling and large-scale convolution to capture the long-distance dependencies among pixels [161,162,[173][174][175].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminating Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Review

Li,

Wang,

Cheikh

2024

Sensors

View full text Add to dashboard Cite

Hyperspectral images (HSIs) contain subtle spectral details and rich spatial contextures of land cover that benefit from developments in spectral imaging and space technology. The classification of HSIs, which aims to allocate an optimal label for each pixel, has broad prospects in the field of remote sensing. However, due to the redundancy between bands and complex spatial structures, the effectiveness of the shallow spectral–spatial features extracted by traditional machine-learning-based methods tends to be unsatisfying. Over recent decades, various methods based on deep learning in the field of computer vision have been proposed to allow for the discrimination of spectral–spatial representations for classification. In this article, the crucial factors to discriminate spectral–spatial features are systematically summarized from the perspectives of feature extraction and feature optimization. For feature extraction, techniques to ensure the discrimination of spectral features, spatial features, and spectral–spatial features are illustrated based on the characteristics of hyperspectral data and the architecture of models. For feature optimization, techniques to adjust the feature distances between classes in the classification space are introduced in detail. Finally, the characteristics and limitations of these techniques and future challenges in facilitating the discrimination of features for HSI classification are also discussed further.

show abstract

“…Chang et al 27 proposed a method based on a consolidated convolutional neural network (C-CNN) composed of 2DCNN and 3DCNN to learn the spatial-spectral features and abstract spatial features of hyperspectral images. Shi et al 28 proposed a model based on multi-scale feature fusion and double attention mechanism to extract features from hyperspectral images. Although the CNN-based models have made some progress in HSI classification, the performance of them is still insufficient.…”

Section: Introductionmentioning

confidence: 99%

Double-branch feature fusion transformer for hyperspectral image classification

Dang

Weng

Hou

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Deep learning methods, particularly Convolutional Neural Network (CNN), have been widely used in hyperspectral image (HSI) classification. CNN can achieve outstanding performance in the field of HSI classification due to its advantages of fully extracting local contextual features of HSI. However, CNN is not good at learning the long-distance dependency relation and dealing with the sequence properties of HSI. Thus, it is difficult to continuously improve the performance of CNN-based models because they cannot take full advantage of the rich and continuous spectral information of HSI. This paper proposes a new Double-Branch Feature Fusion Transformer model for HSI classification. We introduce Transformer into the process of HSI on account of HSI with sequence characteristics. The two branches of the model extract the global spectral features and global spatial features of HSI respectively, and fuse both spectral and spatial features through a feature fusion layer. Furthermore, we design two attention modules to adaptively adjust the importance of spectral bands and pixels for classification in HSI. Experiments and comparisons are carried out on four public datasets, and the results demonstrate that our model outperforms any compared CNN-Based models in terms of accuracy.

show abstract

H2A2Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification

Cited by 13 publications

References 62 publications

LSSMA: Lightweight Spectral–Spatial Neural Architecture With Multiattention Feature Extraction for Hyperspectral Image Classification

LSSMA: Lightweight Spectral–Spatial Neural Architecture With Multiattention Feature Extraction for Hyperspectral Image Classification

Discriminating Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Review

Double-branch feature fusion transformer for hyperspectral image classification

Contact Info

Product

Resources

About