Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network

Li, Rui; Zheng, Shunyi; Duan, Chenxi; Yang, Yang; Wang, Xiqi

doi:10.20944/preprints201912.0059.v2

Cited by 104 publications

(36 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the effectiveness of the proposed method, we compared the proposed SSACC method with several widely used methods such as SVM, SSRN [25], FDSSC [58], DB-MA [59], MAFN [63] and the state-of-the-art double-branch dual-attention mechanism network DBDA [43] methods. All parameters of each classifier were set according to the original papers.…”

Section: Comparing With Other Methodsmentioning

confidence: 99%

“…Zhu et al [22] proposed spectral-spatial attention network by cascading spectral AM and spatial AM in sequential, which emphasizes useful bands and pixels simultaneously. Twobranch spectral-spatial attention networks, such as SSAtt [37], DBMA [42], and DBDA [43], were also proposed for HSIC by exploiting spectral attention sub-network and spatial attention sub-network separately. However, the two sub-networks have no necessary interaction until the eventual combination.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Siamese Spectral Attention With Channel Consistency for Hyperspectral Image Classification

Wang¹,

Yang²,

Liu³

et al. 2021

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

View full text Add to dashboard Cite

Abundant spectral features are the precious wealth of hyperspectral images (HSI). Nevertheless, well-designed spectral feature is still a challenge that affects the performance of the classifier, especially with insufficient number of training samples. To make up the poor discriminability of spectral feature, doublebranch methods are proposed by fusing parallel spectral and spatial branches. However, this structure does nothing to improve the quality of spectral feature, which is regarded as the most valuable information for hyperspectral image information. In this paper, we propose a siamese spectral attention network with channel consistency (SSACC) to focus on obtaining discriminative spectral features, thus improving the generalization ability of the classifier. Two kinds of HSI cubes with different patch sizes are generated as the input of SSACC. The two cubes are divided into top and bottom branches and then be fed into the siamese network to obtain the refined spectral features. Then, self-attention is conducted to interacting with each channel for the spectral features enhancement. Meanwhile, two attention maps are obtained to display the spectral structures of each branch. A channel consistency regularization is performed on the two attention maps by enforcing the two branches to possess similar spectral patterns when identifying the same centric pixel. Extensive experiments conducted on the three HSI datasets verify the superiority of the obtained spectral feature. Furthermore, the proposed method applying convolution only on the spectral domain outperforms the state-of-the-art double-branch methods which integrate the spectral and spatial features simultaneously. Index Terms-spectral siamese; channel consistency; doublebranch; hyperspectral image classification.

show abstract

Section: Comparing With Other Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Siamese Spectral Attention With Channel Consistency for Hyperspectral Image Classification

Wang¹,

Yang²,

Liu³

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…The experimental results show that the DBMA network has a good performance in hyperspectral classification. For further research, Li et al proposed a dual-branch and dual-attention mechanism network (DBDA) [54] based on a new dual attention network (DANet) [55], which has good classification performance in the case of small number of training samples. Roy et al in [56] proposed a Hybrid-SN method, which combines 2D CNN and 3D CNN, and 3DCNN is used to extract the spectral features of the image, while 2D CNN is used to extract the spatial features, and good classification accuracy is obtained.…”

Section: Indexmentioning

confidence: 99%

Hyperspectral Image Classification Based on Dual-Branch Spectral Multiscale Attention Network

Shi¹,

Liao²,

Xiong³

et al. 2021

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

View full text Add to dashboard Cite

“…However, the computational cost is enormous as there are generally several SA modules in the transformer. In [67] and [68], the global salient spectral bands and spatial areas are extracted by the spectral and spatial nonlocal blocks. Both are embedded into the spectral and spatial modules to refine the features, respectively.…”

Section: Introductionmentioning

confidence: 99%

Spatial Attention Guided Residual Attention Network for Hyperspectral Image Classification

Wang

2022

IEEE Access

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification has become a research hotspot. Recently, deep learning-based methods have achieved preferable performances by which the deep spectral-spatial features can be extracted from HSI cubes. However, in complex scenes, due to the diversity of the types of landcover and the bands in high dimensional, these methods are often hampered by the irrelevant spatial areas and the redundant bands, which results in the indistinguishable features and the restricted performance. In this article, a spatial attention guided residual attention network (SpaAG-RAN) is proposed for HSI classification, which contains a spatial attention module (SpaAM), a spectral attention module (SpeAM), and a spectral-spatial feature extraction module (SSFEM). Based on the spectral similarity, the SpaAM is capable of capturing the relevant spatial areas composed of the pixels of the same category as the center pixel from HSI cube with a novel inverted-shifted-scaled sigmoid activation function. The SpeAM aims to select the bands which are beneficial to the spectral features representation. The SSFEM is exploited to extract the discriminating spectral-spatial features. To facilitate the processes of bands selection and features extraction, two well-designed spatial attention masks generated by the SpaAM are employed to guide the works of the SpeAM and the SSFEM, respectively. Moreover, a spatial consistency loss function is installed to maintain the consistency between the two spatial attention masks so that the network enables the distinction of the relevant features exactly. Experimental results on three HSI data sets show that the proposed SpaAG-RAN model can extract the discriminating spectral-spatial features and outperforms the state-of-the-arts. INDEX TERMSHyperspectral image classification, attention mechanism, deep learning, spatial attention, residual network. NINGYANG LI received the B.S. degree in remote sensing science and technology from Henan Polytechnic University, Jiaozuo, China, in 2019. He is currently pursuing the M.S. degree in software engineering with the

show abstract

Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network

Cited by 104 publications

References 0 publications

Siamese Spectral Attention With Channel Consistency for Hyperspectral Image Classification

Siamese Spectral Attention With Channel Consistency for Hyperspectral Image Classification

Hyperspectral Image Classification Based on Dual-Branch Spectral Multiscale Attention Network

Spatial Attention Guided Residual Attention Network for Hyperspectral Image Classification

Contact Info

Product

Resources

About