Hyperspectral Image Classification Based on Multiscale Cross-Branch Response and Second-Order Channel Attention

Shang, Ronghua; Chang, Huidong; Zhang, Weitong; Feng, Jie; Li, Yangyang; Jiao, Licheng

doi:10.1109/tgrs.2022.3184117

Cited by 15 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the SSpaA module, spectral-spatial features are processed using GAP and then a softmax to acquire categories. The GAP is a common and effective component 27 , 58 , 59 . The GAP operation reduces the spatial dimensions of each feature map to a single value per channel by taking the average.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Center-similarity spectral-spatial attention network for hyperspectral image classification

Zhang,

Liang,

Niu

et al. 2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification aims to assign labels to pixels to be classified. The high-dimensional form of HSI and the introduction of spatial information can introduce challenges such as redundant spectral bands and interference pixels. Recently, many methods based on convolutional neural networks and attention mechanisms have been employed to address these issues. However, existing methods often fail to adequately utilize spatial information and exhibit interference pixel diffusion, which may result in these methods being unable to extract discriminative features. In addition, convolutions are not capable of extracting robust features, which results in the poor robustness of recent methods when HSI is rotated. To address these challenges, a center-similarity spectral-spatial attention network model (CS 3 AN) is proposed. First, a center-similarity spectral attention (CSSpeA) module is proposed to exploit the input spatial information rationally to better reduce the impact of redundant bands. Next, a center-similarity rectified spatial attention (CSRSpaA) module that selectively weighs neighboring pixels based on interference pixels to prevent the diffusion phenomenon is provided. Second, a similarity spatial aggregation module is employed to extract robust spectral-spatial features. Finally, the robust features are input into the softmax to get the label. The validity of the CS 3 AN is validated on three different databases.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The GAP is a common and effective component. 27,58,59 The GAP operation reduces the spatial dimensions of each feature map to a single value per channel by taking the average. This significantly reduces the number of parameters.…”

Section: Sspaamentioning

confidence: 99%

Center-similarity spectral-spatial attention network for hyperspectral image classification

Zhang,

Liang,

Niu

et al. 2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…Hao et al [26] proposed a curvature filter-based multiscale feature extraction method (MGCF) by extracting global multi-scale spectral-spatial features using progressive curvature filtering and downsampling operations. 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.…”

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

“…Multiscale feature extraction provides an effective solution to retain more relevant information within a limited number of parameters. Numerous experiments have demonstrated that multiscale features have a significant positive impact on classification performance [32][33][34][35][36].…”

Section: Introductionmentioning

confidence: 99%

MADANet: A Lightweight Hyperspectral Image Classification Network with Multiscale Feature Aggregation and a Dual Attention Mechanism

Cui,

Wen,

Song

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral remote sensing images, with their continuous, narrow, and rich spectra, hold distinct significance in the precise classification of land cover. Deep convolutional neural networks (CNNs) and their variants are increasingly utilized for hyperspectral classification, but solving the conflict between the number of model parameters, performance, and accuracy has become a pressing challenge. To alleviate this problem, we propose MADANet, a lightweight hyperspectral image classification network that combines multiscale feature aggregation and a dual attention mechanism. By employing depthwise separable convolution, multiscale features can be extracted and aggregated to capture local contextual information effectively. Simultaneously, the dual attention mechanism harnesses both channel and spatial dimensions to acquire comprehensive global semantic information. Ultimately, techniques such as global average pooling (GAP) and full connection (FC) are employed to integrate local contextual information with global semantic knowledge, thereby enabling the accurate classification of hyperspectral pixels. The results from the experiments conducted on representative hyperspectral images demonstrate that MADANet not only attains the highest classification accuracy but also maintains significantly fewer parameters compared to the other methods. Experimental results show that our proposed framework significantly reduces the number of model parameters while still achieving the highest classification accuracy. As an example, the model has only 0.16 M model parameters in the Indian Pines (IP) dataset, but the overall accuracy is as high as 98.34%. Similarly, the framework achieves an overall accuracy of 99.13%, 99.17%, and 99.08% on the University of Pavia (PU), Salinas (SA), and WHU Hi LongKou (LongKou) datasets, respectively. This result exceeds the classification accuracy of existing state-of-the-art frameworks under the same conditions.

show abstract

Hyperspectral Image Classification Based on Multiscale Cross-Branch Response and Second-Order Channel Attention

Cited by 15 publications

References 55 publications

Center-similarity spectral-spatial attention network for hyperspectral image classification

Center-similarity spectral-spatial attention network for hyperspectral image classification

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

MADANet: A Lightweight Hyperspectral Image Classification Network with Multiscale Feature Aggregation and a Dual Attention Mechanism

Contact Info

Product

Resources

About