Multi-Objective Optimization of Hyperspectral Band Selection Based on Attention Mechanism

Shihao Guan; Guang Yang; Shan Lu; Yanyu Fu

doi:10.3788/AOS202040.2128002

Journals >Acta Optica Sinica >Volume 40 >Issue 21 >Page 2128002 > Article

Acta Optica Sinica
Vol. 40, Issue 21, 2128002 (2020)

Multi-Objective Optimization of Hyperspectral Band Selection Based on Attention Mechanism

Shihao Guan¹, Guang Yang^1、*, Shan Lu², and Yanyu Fu¹

Author Affiliations

¹School of Aviation Operations and Services, Aviation University of Air Force, Changchun, Jilin 130022, China

²School of Geographic Science, Northeast Normal University, Changchun, Jilin 130024, China

show less

DOI: 10.3788/AOS202040.2128002 Cite this Article Set citation alerts

Shihao Guan, Guang Yang, Shan Lu, Yanyu Fu. Multi-Objective Optimization of Hyperspectral Band Selection Based on Attention Mechanism[J]. Acta Optica Sinica, 2020, 40(21): 2128002 Copy Citation Text

show less

Fig. 1. SENet structure

Download full size

Fig. 2. Band selection model structure

Download full size

Fig. 3. True color image and ground truth map of Botswana data set. (a) True color image; (b) ground truth map

Download full size

Fig. 4. True color image and ground truth map of Indian Pines data set. (a) True color image; (b) ground truth map

Download full size

Fig. 5. SENet structure in the experiment

Download full size

Fig. 6. Overall classification accuracy, training loss, and band weight changes in the Botswana data set. (a) Overall classification accuracy; (b) training loss; (c) band weight thermal map

Download full size

Fig. 7. Overall classification accuracy, training loss and band weight changes on the Indian Pines data set. (a) Overall classification accuracy; (b) training loss; (c) band weight thermal map

Download full size

Fig. 8. Overall classification accuracy, average classification accuracy and Kappa coefficient of each algorithm in the Botswana data set. (a) Overall classification accuracy; (b) average classification accuracy; (c) Kappa coefficient

Download full size

Fig. 9. Average spectral divergence of each algorithm on the Botswana data set

Download full size

Fig. 10. Overall classification accuracy, average classification accuracy and Kappa coefficient of each algorithm in the Indian Pines data set. (a) Overall classification accuracy; (b) average classification accuracy; (c) Kappa coefficient

Download full size

Fig. 11. Average spectral divergence of each algorithm on the Indian Pines data set

Download full size

Module	Layer	Input size	Output size	Activation
	Input		1×1×b
Attention module	FC-1(fully connected layer)	1×1×b	1×1×(b/16)	ReLU
	FC-2(fully connected layer)	1×1×(b/16)	1×1×b	Sigmoid
	Encoder-1(autoencoder)	1×1×b	1×1×256
	BN-1(batch normalization)	1×1×256	1×1×256	ReLU
	Encoder-2(autoencoder)	1×1×256	1×1×128
	BN-2(batch normalization)	1×1×128	1×1×128	ReLU
	Encoder-3(autoencoder)	1×1×128	1×1×64
	BN-3(batch normalization)	1×1×64	1×1×64	ReLU
Reconstruction module	Encoder-4(autoencoder)	1×1×64	1×1×64
	BN-4(batch normalization)	1×1×64	1×1×64	ReLU
	Decoder-1(autoencoder)	1×1×64	1×1×128
	BN-5(batch normalization)	1×1×128	1×1×128	ReLU
	Decoder-2(autoencoder)	1×1×128	1×1×256
	BN-6(batch normalization)	1×1×256	1×1×256	ReLU
	Decoder-3(autoencoder)	1×1×256	1×1×b	Sigmoid
Classification module	Latent vector	1×1×64	1×1×64
	FC-3(fully connected layer)	1×1×64	Number of class	Softmax

Table 1. Data size and activation function change in the model

Item	Botswana	Indian Pines
Shooting area	Okavango Delta, Botswana	Indiana, USA
Imaging spectrometer	Hyperion	AVIRIS
Spectral range /nm	400-2500	400-2500
Number of wavelengths (remove strong noise and water vapor band)	145	200
Image size /(pixel×pixel)	1476×256	145×145
Spatial resolution /m	30	20
Sample size	3248	10249
Object types	14	16

Table 2. Hyperspectral image data set

γ	Botswana				Indian Pines
γ	OA /%	AA /%		Kappa	OA /%	AA /%		Kappa
0.1	88.9		89.5				0.873		73.1	71.4	0.708
0.3	89.3		89.8				0.886		73.6	71.5	0.706
0.5	88.6		87.1				0.869		74.3	70.4	0.712
0.7	87.2		86.8				0.853		72.1	69.5	0.698
0.9	85.3		86.7				0.839		69.7	66.1	0.664

Table 3. Experimental results of two data sets with different weight coefficients

Shihao Guan, Guang Yang, Shan Lu, Yanyu Fu. Multi-Objective Optimization of Hyperspectral Band Selection Based on Attention Mechanism[J]. Acta Optica Sinica, 2020, 40(21): 2128002

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information