Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The proposed LSANet architecture for LULC in HSI.

More »

Fig 1 Expand

Fig 2.

Illustration of standard GSA (2(a)), axial self-attention (2(b)), cross shaped attention (2(c)) and the proposed LS-attention (2(d)).

In 2(b), 2(c) and 2(d), the shadow area represents the input features split into different groups on which SA is conducted, and the yellow dot can directly interact with the token covered in the shadow region. Here, represent height, width and channel of the image, respectively.

More »

Fig 2 Expand

Fig 3.

Illustration of (a) standard embedding in ViT, (b) proposed CPE, (c) PEG block.

More »

Fig 3 Expand

Fig 4.

Details of the Pavia University (PU) dataset with samples and color coding.

More »

Fig 4 Expand

Fig 5.

Details of the Indiana Pines (IP) dataset with samples and color coding.

More »

Fig 5 Expand

Fig 6.

Details of the Salinas Valley (SV) dataset with samples samples and color coding.

More »

Fig 6 Expand

Fig 7.

Details of the Botswana dataset with samples samples and color coding.

More »

Fig 7 Expand

Table 1.

Performance comparison on the PU dataset.

More »

Table 1 Expand

Table 2.

Quantitative results comparison on the IP dataset.

More »

Table 2 Expand

Table 3.

Performance comparison on the Botswana dataset.

More »

Table 3 Expand

Table 4.

Performance comparison on the SV dataset.

More »

Table 4 Expand

Fig 8.

The visual map on PU dataset.

(a)GT (b)2D-CNN (c)3D-CNN (d)HybridSN (e)CSIL (f)SF (g) DSGSF (h)MF (i) SS1DSwin and (j) LSANet.

More »

Fig 8 Expand

Fig 9.

Illustration of the visual map on IP dataset.

(a)GT (b)2D-CNN (c)3D-CNN (d)HybridSN (e)CSIL (f)SF (g) DSGSF (h)MF (i) SS1DSwin and (j) LSANet.

More »

Fig 9 Expand

Fig 10.

The visual map on SV dataset.

(a)GT (b)2D-CNN (c)3D-CNN (d)HybridSN (e)CSIL (f)SF (g) DSGSF (h)MF (i) SS1DSwin and (j) LSANet.

More »

Fig 10 Expand

Fig 11.

The visual map on Botswana dataset.

(a)GT (b)2D-CNN (c)3D-CNN (d)HybridSN (e)CSIL (f)SF (g) DSGSF (h)MF (i) SS1DSwin and (j) LSANet.

More »

Fig 11 Expand

Fig 12.

Illustration of limpid size on IP, PU, SV and Botswana datasets.

More »

Fig 12 Expand

Table 5.

Performance evaluation using different components.

More »

Table 5 Expand

Fig 13.

Illustration of the (a) learning rate and (b) batch size on the IP, PU, SV and Botswana datasets.

More »

Fig 13 Expand

Table 6.

LSANet performance on IP dataset with CPE and zero padding.

More »

Table 6 Expand

Fig 14.

Training time comparison on PU, IP, SV, and Botswana datasets.

More »

Fig 14 Expand

Table 7.

Performance comparison using different attention mechanisms.

More »

Table 7 Expand

Table 8.

Performance comparison using different encoding techniques.

More »

Table 8 Expand

Table 9.

Parameters and flops comparison.

More »

Table 9 Expand