# EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

- We propose a novel BS scoring function that can consider the redundancy and representativeness of the bands simultaneously. To the best of our knowledge, this is the first time that the redundancy and representativeness of bands are explored simultaneously in the attention and reconstruction network-based BS method. Specifically, we design an adaptive balance coefficient that can balance the representativeness metric and the redundancy metric to solve the problem that the scoring function has different sensitivities to these two metrics. According to the proposed BS scoring function, a band subset with a good representation of the original band set and less redundant information can be selected, which is conducive to downstream tasks.
- The proposed attention reconstruction network-based BS architecture adds the spectral angle error as one of the evaluation criteria of the reconstruction effect, which is proposed for the first time. As a result, unlike the traditional reconstruction network that only uses MSE as the reconstruction criterion, our attention reconstruction network-based BS architecture combines MSE and spectral angle error to improve the applicability of the model.
- A novel unsupervised BS framework in which attention weights and bands are closely connected is proposed, which helps to resolve the problem that correspondence between the band and its weight is indirect in current attention mechanism-based methods.

## 2. Related Works

#### 2.1. Attention Mechanism

#### 2.2. Autoencoder

## 3. The Proposed Method

#### 3.1. EBARec

#### 3.2. Band Selection Module Based on Representativeness and Redundancy

Algorithm 1 The EBARec-BS Algorithm |

Input: HSI cube $x\in {\mathbb{R}}^{W\times H\times B}$, the number of selected bands n, and EBARec-BS hyper-parameters.Step1: Preprocess HSI and generate training samples. Step2: Train EBARec network. while Model is convergent or maximum iteration is met do1: Sample a batch of training samples ${\mathbf{X}}_{\mathrm{p}}$. 2: Calculate bands weights: $\mathbf{\omega}={\mathrm{F}}_{\mathrm{EBA}}({\mathbf{X}}_{\mathrm{p}};{\Theta}_{\mathrm{p}})$. 3: Reweight spectral bands: $\mathbf{Z}={\mathbf{X}}_{\mathrm{p}}\otimes \mathbf{\omega}$. 4: Reconstruct spectral bands: ${\widehat{\mathbf{X}}}_{\mathrm{p}}={\mathrm{F}}_{\mathrm{Rec}}(\mathbf{Z};{\Theta}_{\mathrm{c}})$. 5: Update ${\Theta}_{\mathrm{p}}$ and ${\Theta}_{\mathrm{c}}$ by minimizing Equation (15) using Adam algorithm. end whileStep3: Calculate average attention weight of each band according to Equation (16). Step4: Set counter $k=0$. Step5: Band selection. while$kn$do1: For the ith band ${x}_{i},(i=1,2,\cdots ,B)$, calculate its score according to Equation (21). Note that if the ith band ${x}_{i}$ has already been selected, its score would not be calculated and compared. 2: Find the band with the highest score and add it to the selected band subset. 3: $k\leftarrow k+1$. end whileOutput: n selected bands. |

## 4. Experiments

#### 4.1. Datasets and Experimental Setup

#### 4.2. Classification Results

#### 4.3. Band Correlation Comparison

#### 4.4. Robustness to Noisy Bands

#### 4.5. Summary

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Hughes, G. On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory
**1968**, 14, 55–63. [Google Scholar] [CrossRef] [Green Version] - Fisher, R.A. The use of multiple measurements in taxonomic problems. Ann. Eugen.
**1936**, 7, 179–188. [Google Scholar] [CrossRef] - Fang, Y.; Li, H.; Ma, Y.; Liang, K.; Hu, Y.; Zhang, S.; Wang, H. Dimensionality reduction of hyperspectral images based on robust spatial information using locally linear embedding. IEEE Geosci. Remote Sens. Lett.
**2014**, 11, 1712–1716. [Google Scholar] [CrossRef] - Liu, Y.; Li, X.; Feng, Y.; Zhao, L.; Zhang, W. Representativeness and Redundancy-Based Band Selection for Hyperspectral Image Classification. Int. J. Remote Sens.
**2021**, 42, 3534–3562. [Google Scholar] [CrossRef] - Song, M.; Shang, X.; Wang, Y.; Yu, C.; Chang, C.I. Class Information-Based Band Selection for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens.
**2019**, 57, 8394–8416. [Google Scholar] [CrossRef] - Yang, H.; Du, Q.; Su, H.; Sheng, Y. An efficient method for supervised hyperspectral band selection. IEEE Geosci. Remote Sens. Lett.
**2010**, 8, 138–142. [Google Scholar] [CrossRef] - Zhang, W.; Li, X.; Zhao, L. Discovering the Representative Subset with Low Redundancy for Hyperspectral Feature Selection. Remote Sens.
**2019**, 11, 1341. [Google Scholar] [CrossRef] [Green Version] - Geng, X.; Sun, K.; Ji, L.; Zhao, Y. A fast volume-gradient-based band selection method for hyperspectral image. IEEE Trans. Geosci. Remote Sens.
**2014**, 52, 7111–7119. [Google Scholar] [CrossRef] - Zhang, W.; Li, X.; Dou, Y.; Zhao, L. A geometry-based band selection approach for hyperspectral image analysis. IEEE Trans. Geosci. Remote Sens.
**2018**, 56, 4318–4333. [Google Scholar] [CrossRef] - Xu, Y.; Du, Q.; Younan, N.H. Particle swarm optimization-based band selection for hyperspectral target detection. IEEE Geosci. Remote Sens. Lett.
**2017**, 14, 554–558. [Google Scholar] [CrossRef] - Gao, J.; Du, Q.; Gao, L.; Sun, X.; Zhang, B. Ant colony optimization-based supervised and unsupervised band selections for hyperspectral urban data classification. J. Appl. Remote Sens.
**2014**, 8, 085094. [Google Scholar] [CrossRef] - Chang, C.I.; Du, Q.; Sun, T.L.; Althouse, M.L. A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens.
**1999**, 37, 2631–2641. [Google Scholar] [CrossRef] [Green Version] - Kim, J.H.; Kim, J.; Yang, Y.; Kim, S.; Kim, H.S. Covariance-based band selection and its application to near-real-time hyperspectral target detection. Opt. Eng.
**2017**, 56, 053101. [Google Scholar] [CrossRef] - Chang, C.I.; Wang, S. Constrained band selection for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens.
**2006**, 44, 1575–1585. [Google Scholar] [CrossRef] - Sun, K.; Geng, X.; Ji, L. Exemplar component analysis: A fast band selection method for hyperspectral imagery. IEEE Geosci. Remote Sens. Lett.
**2015**, 12, 998–1002. [Google Scholar] - Sun, W.; Peng, J.; Yang, G.; Du, Q. Fast and Latent Low-Rank Subspace Clustering for Hyperspectral Band Selection. IEEE Trans. Geosci. Remote Sens.
**2020**, 58, 3906–3915. [Google Scholar] [CrossRef] - Feng, Y.; Yuan, Y.; Lu, X. A non-negative low-rank representation for hyperspectral band selection. Int. J. Remote Sens.
**2016**, 37, 4590–4609. [Google Scholar] [CrossRef] - Wang, Q.; Lin, J.; Yuan, Y. Salient band selection for hyperspectral image classification via manifold ranking. IEEE Trans. Neural Netw. Learn. Syst.
**2016**, 27, 1279–1289. [Google Scholar] [CrossRef] - Yuan, Y.; Zheng, X.; Lu, X. Discovering diverse subset for unsupervised hyperspectral band selection. IEEE Trans. Image Process.
**2016**, 26, 51–64. [Google Scholar] [CrossRef] - Sun, K.; Geng, X.; Ji, L. A New Sparsity-Based Band Selection Method for Target Detection of Hyperspectral Image. IEEE Geosci. Remote Sens. Lett.
**2015**, 12, 329–333. [Google Scholar] [CrossRef] - Cai, Y.; Liu, X.; Cai, Z. BS-Nets: An End-to-End Framework for Band Selection of Hyperspectral Image. IEEE Trans. Geosci. Remote Sens.
**2020**, 58, 1969–1984. [Google Scholar] [CrossRef] [Green Version] - Hong, D.; Gao, L.; Yao, J.; Zhang, B.; Plaza, A.; Chanussot, J. Graph Convolutional Networks for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens.
**2021**, 59, 5966–5978. [Google Scholar] [CrossRef] - Zhao, B.; Wu, Y.; Guan, X.; Gao, L.; Zhang, B. An Improved Aggregated-Mosaic Method for the Sparse Object Detection of Remote Sensing Imagery. Remote Sens.
**2021**, 13, 2602. [Google Scholar] [CrossRef] - Yao, J.; Meng, D.; Zhao, Q.; Cao, W.; Xu, Z. Nonconvex-sparsity and nonlocal-smoothness-based blind hyperspectral unmixing. IEEE Trans. Image Process.
**2019**, 28, 2991–3006. [Google Scholar] [CrossRef] - Dou, Z.; Gao, K.; Zhang, X.; Wang, H.; Han, L. Band Selection of Hyperspectral Images Using Attention-Based Autoencoders. IEEE Geosci. Remote Sens. Lett.
**2021**, 18, 147–151. [Google Scholar] [CrossRef] - Bahdanau, D.; Cho, K.; Bengio, Y. Neural Machine Translation by Jointly Learning to Align and Translate. arXiv
**2014**, arXiv:1409.0473. [Google Scholar] - Chorowski, J.; Bahdanau, D.; Serdyuk, D.; Cho, K.; Bengio, Y. Attention-based models for speech recognition. arXiv
**2015**, arXiv:1506.07503. [Google Scholar] - Galassi, A.; Lippi, M.; Torroni, P. Attention in natural language processing. IEEE Trans. Neural Netw. Learn. Syst.
**2020**. [Google Scholar] [CrossRef] - Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is all you need. arXiv
**2017**, arXiv:1706.03762. [Google Scholar] - Wang, F.; Tax, D.M. Survey on the attention based RNN model and its applications in computer vision. arXiv
**2016**, arXiv:1601.06823. [Google Scholar] - Serre, T.; Wolf, L.; Poggio, T. Object recognition with features inspired by visual cortex. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 20–25 June 2005; Volume 2, pp. 994–1000. [Google Scholar]
- Masci, J.; Meier, U.; Cireşan, D.; Schmidhuber, J. Stacked convolutional auto-encoders for hierarchical feature extraction. In Artificial Neural Networks and Machine Learning—ICANN 2011, Proceedings of the International Conference on Artificial Neural Networks, Espoo, Finland, 14–17 June 2011; Springer: Berlin/Heidelberg, Germany, 2011; pp. 52–59. [Google Scholar]
- Wang, Q.; Wu, B.; Zhu, P.; Li, P.; Hu, Q. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 16–18 June 2020. [Google Scholar]
- Liu, C.; Li, J.; He, L.; Plaza, A.; Li, S.; Li, B. Naive Gabor Networks for Hyperspectral Image Classification. IEEE Trans. Neural Netw. Learn. Syst.
**2021**, 32, 376–390. [Google Scholar] [CrossRef] [Green Version] - Melgani, F.; Bruzzone, L. Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci. Remote Sens.
**2004**, 42, 1778–1790. [Google Scholar] [CrossRef] [Green Version] - Kang, X.; Li, S.; Benediktsson, J.A. Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering. IEEE Trans. Geosci. Remote Sens.
**2014**, 52, 2666–2677. [Google Scholar] [CrossRef] - Mitra, P.; Murthy, C.; Pal, S. Unsupervised feature selection using feature similarity. IEEE Trans. Pattern Anal. Mach. Intell.
**2002**, 24, 301–312. [Google Scholar] [CrossRef] - Tarabalka, Y.; Chanussot, J.; Benediktsson, J.A. Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognit.
**2010**, 43, 2367–2379. [Google Scholar] [CrossRef] [Green Version] - Rifkin, R.; Klautau, A. In Defense of One-Vs-All Classification. J. Mach. Learn. Res.
**2004**, 5, 101–141. [Google Scholar]

**Figure 3.**Grayscale images of some bands of the three datasets. (

**a**) Band 170 of Indian Pines, (

**b**) Band 50 of Pavia University, (

**c**) Band 100 of Salinas.

**Figure 4.**Overall classification accuracies of using the band subset selected by different BS methods from three different data sets. (

**a**) Indian Pines-SVM, (

**b**) PaviaU-SVM, (

**c**) Salinas-SVM, (

**d**) Indian Pines-EPF-G-g, (

**e**) PaviaU-EPF-G-g, (

**f**) Salinas-EPF-G-g.

**Figure 5.**SVM classification maps of using the fifteen bands selected by different methods from the Indian Pines data set. (

**a**) Ground truth, (

**b**) MVPCA, (

**c**) LCMVBCC, (

**d**) LCMVBCM, (

**e**) ECA, (

**f**) OPBS, (

**g**) BS-Net-Conv, (

**h**) EBARec-BS.

**Figure 6.**SVM classification maps of using the ten bands selected by different methods from the Pavia University data set. (

**a**) Ground truth, (

**b**) MVPCA, (

**c**) LCMVBCC, (

**d**) LCMVBCM, (

**e**) ECA, (

**f**) OPBS, (

**g**) BS-Net-Conv, (

**h**) EBARec-BS.

**Figure 7.**SVM classification maps of using the fifteen bands selected by different methods from the Salinas data set. (

**a**) Ground truth, (

**b**) MVPCA, (

**c**) LCMVBCC, (

**d**) LCMVBCM, (

**e**) ECA, (

**f**) OPBS, (

**g**) BS-Net-Conv, (

**h**) EBARec-BS.

**Figure 8.**Parameter sensitivity analysis of the proposed EBARec-BS method in terms of $\eta $ and $\gamma $ on the Indian Pines dataset. (

**a**) SVM classification, (

**b**) EPF-G-g classification.

**Figure 9.**Spectrum curves of the categories on the Indian Pines data set. The vertical lines denote the fifteen bands selected by the different BS methods. (

**a**) MVPCA, (

**b**) LCMVBCC, (

**c**) LCMVBCM, (

**d**) ECA, (

**e**) OPBS, (

**f**) BS-Net-Conv, (

**g**) EBARec-BS.

**Figure 10.**Spectrum curves of the categories on the Pavia University data set. The vertical lines denote the ten bands selected by the different BS methods. (

**a**) MVPCA, (

**b**) LCMVBCC, (

**c**) LCMVBCM, (

**d**) ECA, (

**e**) OPBS, (

**f**) BS-Net-Conv, (

**g**) EBARec-BS.

**Figure 11.**Spectrum curves of the categories on the Salinas data set. The vertical lines denote the fifteen bands selected by the different BS methods. (

**a**) MVPCA, (

**b**) LCMVBCC, (

**c**) LCMVBCM, (

**d**) ECA, (

**e**) OPBS, (

**f**) BS-Net-Conv, (

**g**) EBARec-BS.

Dataset | Indian Pines | Pavia University | Salinas |
---|---|---|---|

Pixel | 145 × 145 | 610 × 340 | 512 × 217 |

Band | 185 | 103 | 224 |

Used class | 16 | 9 | 16 |

**Table 2.**Overall accuracies (OA) (%) and average accuracies (AA) (%) of using the fifteen/ten bands selected from different datasets. (The bold denotes the best result achieved by BS methods.)

Indian (15 Bands) | SVM | EPF-G-g | ||

OA (%) | AA (%) | OA (%) | AA (%) | |

1. MVPCA | 64.81 | 50.83 | 79.17 | 67.51 |

2. LCMVBCC | 58.95 | 49.74 | 71.17 | 62.01 |

3. LCMVBCM | 66.90 | 60.98 | 80.38 | 73.33 |

4. ECA | 75.16 | 65.25 | 88.80 | 80.03 |

5. OPBS | 72.33 | 62.97 | 87.31 | 80.38 |

6. BS-Net-Conv | 78.91 | 72.27 | 91.20 | 85.25 |

7. EBARec-BS | 80.90 | 74.30 | 93.07 | 88.60 |

PaviaU (10 Bands) | SVM | EPF-G-g | ||

OA (%) | AA (%) | OA (%) | AA (%) | |

1. MVPCA | 70.95 | 55.99 | 82.01 | 70.92 |

2. LCMVBCC | 69.70 | 63.76 | 79.79 | 80.29 |

3. LCMVBCM | 77.50 | 67.97 | 85.25 | 83.25 |

4. ECA | 83.86 | 71.88 | 92.46 | 83.87 |

5. OPBS | 86.39 | 76.28 | 95.29 | 86.80 |

6. BS-Net-Conv | 87.31 | 77.11 | 96.76 | 87.57 |

7. EBARec-BS | 87.34 | 77.15 | 97.12 | 87.59 |

Salinas (15 Bands) | SVM | EPF-G-g | ||

OA (%) | AA (%) | OA (%) | AA (%) | |

1. MVPCA | 84.91 | 84.10 | 91.53 | 90.14 |

2. LCMVBCC | 87.88 | 87.82 | 93.06 | 91.87 |

3. LCMVBCM | 89.62 | 89.21 | 93.91 | 91.98 |

4. ECA | 92.01 | 90.23 | 97.79 | 93.24 |

5. OPBS | 92.04 | 90.10 | 94.61 | 92.13 |

6. BS-Net-Conv | 90.27 | 89.07 | 97.03 | 92.93 |

7. EBARec-BS | 93.42 | 90.97 | 98.21 | 93.35 |

**Table 3.**Fifteen bands selected by different methods from the Indian Pines dataset (the bold denotes noisy bands).

Fifteen Selected Bands | ||||||||
---|---|---|---|---|---|---|---|---|

MVPCA | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 |

29 | 30 | 31 | 32 | 33 | 41 | 42 | ||

LCMVBCC | 108 | 119 | 152 | 154 | 155 | 156 | 158 | 159 |

160 | 161 | 162 | 165 | 196 | 218 | 220 | ||

LCMVBCM | 119 | 120 | 123 | 130 | 153 | 155 | 159 | 160 |

165 | 171 | 174 | 185 | 196 | 199 | 209 | ||

ECA | 1 | 2 | 18 | 31 | 32 | 35 | 36 | 37 |

46 | 57 | 61 | 62 | 75 | 100 | 101 | ||

OPBS | 1 | 18 | 20 | 23 | 29 | 32 | 34 | 35 |

42 | 57 | 61 | 74 | 75 | 88 | 89 | ||

BS-Net-Conv | 1 | 6 | 42 | 68 | 99 | 105 | 106 | 107 |

108 | 123 | 150 | 153 | 162 | 194 | 203 | ||

EBARec-BS | 17 | 18 | 19 | 20 | 27 | 33 | 53 | 130 |

141 | 167 | 168 | 169 | 173 | 182 | 202 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Liu, Y.; Li, X.; Hua, Z.; Zhao, L.
EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection. *Remote Sens.* **2021**, *13*, 3602.
https://doi.org/10.3390/rs13183602

**AMA Style**

Liu Y, Li X, Hua Z, Zhao L.
EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection. *Remote Sensing*. 2021; 13(18):3602.
https://doi.org/10.3390/rs13183602

**Chicago/Turabian Style**

Liu, Yufei, Xiaorun Li, Ziqiang Hua, and Liaoying Zhao.
2021. "EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection" *Remote Sensing* 13, no. 18: 3602.
https://doi.org/10.3390/rs13183602