*3.3. Information Interaction Block*

The main function of the IIB is to realize information interaction in SSIN. As shown in Figure 3, we first extract spectral information of the input spectral-branch feature by a convolutional layer with 3 × 3 kernel size, then the extracted spectral information is concatenated with the input spatial-branch feature and further use a 1 × 1 convolutional layer to update the spatial information. Note that we add the input spatial-branch feature to the updated spatial information to achieve local residual learning.

**Figure 3.** Schematic diagram of the information interaction block, "⊕"denotes elementwise addition, and "⊗" denotes matrix multiplication.

Simultaneously, we extract the spatial information of the spatial branch using a convolutional layer and then concatenated it with the input of the spectral-branch feature, but the difference is that we extract the spatial information of the spatial-branch output port. In

this way, the updated spatial information can be used to guide spectral information updata. In summary, the information interaction block can be formulated as:

$$I\_{spa}^{n} = \text{ReLU}\left(H\_{1 \times 1}\left(\left[H\_{3 \times 3}\left(I\_{spa}^{n-1}\right), I\_{spa}^{n-1}\right]\right)\right) \quad + \quad I\_{spa}^{n-1} \tag{8}$$

$$I\_{\rm spc}^{\rm n} = \text{ReLU}\left(H\_{1 \times 1}\left(\left[H\_{3 \times 3}\left(I\_{\rm spn}^{\rm n}\right), I\_{\rm spc}^{\rm n-1}\right]\right)\right) \; + \; I\_{\rm spc}^{\rm n-1} \tag{9}$$

where *H*1×<sup>1</sup> and *H*3×<sup>3</sup> represent convolution operation with 1 × 1 kernel size and 3 × 3 kernel size, respectively. Re*LU*(·) represents the Re*LU* activation function [49].
