A Spectral and Spatial Attention Network for Change Detection in Hyperspectral Images

Gong, Maoguo; Jiang, Fenlong; Qin, A. K.; Liu, Tongfei; Zhan, Tao; Lu, Di; Zheng, Hanhong; Zhang, Mingyang

doi:10.1109/tgrs.2021.3139077

Cited by 40 publications

(20 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MHSA mechanism of the BERT model captures rich nonlocal spatial contextual information but ignores the representation of local spatial information on HSIs. In this paper, we guide HSI’s local spatial feature extraction through the spatial augmented learning module to obtain an optimal input and then send it to the BERT module for further feature extraction and classification tasks 35 . The diagram of the spatially augmented learning module is shown in Fig.…”

Section: Modified Bert Network Structurementioning

confidence: 99%

Spatially augmented guided sequence-based bidirectional encoder representation from transformer networks for hyperspectral classification studies

Zhang,

Bao,

Liang

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

In recent years, bidirectional encoder representation from transformers (BERT) models have achieved superior performance in hyperspectral images (HSIs). It can capture the long-range correlations between HSI elements, but the local space and spectral band information of HSI is insufficient. We propose a spatially augmented guided sequence BERT network for HSI classification study, referred to as SAS-BERT, which makes more effective use of HSI's spatial and spectral information by improving the BERT model. First, a spatial augmentation learning module is added in the preprocessing stage to obtain more significant spatial features before the input network and better guide the spatial sequence. Then a spectral correlation module was used to represent the spectral band features of the HSI and to establish a correlation with the spatial location of the images to obtain better classification performance. Experimental results on three datasets show that the method proposed achieves better classification performance than other state-of-the-art methods.

show abstract

Section: Modified Bert Network Structurementioning

confidence: 99%

Spatially augmented guided sequence-based bidirectional encoder representation from transformer networks for hyperspectral classification studies

Zhang,

Bao,

Liang

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

show abstract

“…Then, LSTM is also used to analyze temporal dependence between multitemporal images. Gong et al [33] proposed a spectral and spatial attention network (S2AN), which uses multiple repetitive spatial attention modules with adaptive Gaussian distributions to gradually enhance CD-related features. In summary, the attention mechanisms can help to notice the changing regions of the spatial-spectral information.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Diff-Changed Feature Fusion Network for Hyperspectral Image Change Detection

Luo

Zhou

Liu

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, due to the locality of traditional convolution, these methods are difficult to capture the global semantic interaction and the context relationships among different-level features. Then, the new CNN-based methods [27], [28], [29] are equipped with dilated convolutions [30], [31] or attention mechanisms [32], [33] to alleviate this problem. They still have bottlenecks in extracting global information.…”

Section: Introductionmentioning

confidence: 99%

Context and Difference Enhancement Network for Change Detection

Song

Dong

2022

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

View full text Add to dashboard Cite

At present, convolution neural networks have achieved good performance in remote sensing image change detection. However, due to the locality of convolution, these methods are difficult to capture the global context relationships among different-level features. To alleviate this issue, we propose a context and difference enhancement network (CDENet) for change detection, which can strongly model global context relationships and enhance the change difference. Specifically, our backbone is the dual TransUNet, which is based on U-Net and equipped with transformer block in the encoder. The dual TransUNet is used to extract bi-temporal features. Then, the features are encoded as the input sequence, which is conducive to modeling the global context. Moreover, we design the content difference enhancement module to process the dual features of each layer in the encoder. The designed module can increase the spatial attention of difference regions to enhance the change difference features. In the decoder, we adopt a simple crosslayer feature fusion to combine the upsampled features with the high-resolution features, which is used to generate more accurate results. Finally, we adopt a novel loss to supervise the accuracy of results in regions and pixels. The experiments on two public change detection datasets demonstrate that our CDENet has strong competitiveness and performs better than the state-ofthe-art methods.

show abstract

A Spectral and Spatial Attention Network for Change Detection in Hyperspectral Images

Cited by 40 publications

References 58 publications

Spatially augmented guided sequence-based bidirectional encoder representation from transformer networks for hyperspectral classification studies

Spatially augmented guided sequence-based bidirectional encoder representation from transformer networks for hyperspectral classification studies

Multiscale Diff-Changed Feature Fusion Network for Hyperspectral Image Change Detection

Context and Difference Enhancement Network for Change Detection

Contact Info

Product

Resources

About