Table 2.

The number of channels and output dimensions of each layer.

Layer name	Operate	Kernel size	Stride	Output size	Channels
Input				224 × 224	3
Top layer	conv2d	7 × 7	2	112 × 112	16
	Max Pool2d	3 × 3	2	56 × 56	16
	R-block1	$\left(\frac{\text{conv}2\text{d},1\times 1,4}{\begin{array}{c}\text{conv}2\text{d},3\times 3,4\\ \text{conv}2\text{d},1\times 1,16\end{array}}\right)\times 1$	1 1 1	56 × 56	16
Middle layer	R-block5	$\left(\frac{\text{conv}2\text{d},1\times 1,4}{\begin{array}{c}\text{conv}2\text{d},3\times 3,4\\ \text{conv}2\text{d},1\times 1,16\end{array}}\right)\times 1$	1 1 1	56 × 56	16
Bottom layer	RA-UNET			56 × 56	16
Top layer	R-block2	$\left(\frac{\text{conv}2\text{d},1\times 1,8}{\begin{array}{c}\text{conv}2\text{d},3\times 3,8\\ \text{conv}2\text{d},1\times 1,32\end{array}}\right)\times 1$	1 2 1	28 × 28	32
	R-block3	$\left(\frac{\text{conv}2\text{d},1\times 1,16}{\begin{array}{c}\text{conv}2\text{d},3\times 3,16\\ \text{conv}2\text{d},1\times 1,64\end{array}}\right)\times 1$	1 2 1	14 × 14	64
	R-block4	$\left(\frac{\text{conv}2\text{d},1\times 1,16}{\begin{array}{c}\text{conv}2\text{d},3\times 3,16\\ \text{conv}2\text{d},1\times 1,64\end{array}}\right)\times 1$	1 2 1	7 × 7	64
	Avg Pool2d	7 × 7	1	1 × 1	64
Output				4