Table 2.

The architecture of the proposed method.

Layer Name	Output Size	Layer
STN	224 × 224	Localization network, grid generator, sampler
Conv1	112 × 112	7 × 7, 64, stride 2
Max pooling	56 × 56	3 × 3, stride 2
Stage 2	56 × 56	$\left[\begin{array}{cc}1\times 1,& 64\\ 3\times 3,& 64\\ 1\times 1,& 256\end{array}\right]\times 3$, Mish
Stage 3	28 × 28	$\left[\begin{array}{cc}1\times 1,& 128\\ 3\times 3,& 128\\ 1\times 1,& 512\end{array}\right]\times 4$, Mish
Stage 4	14 × 14	$\left[\begin{array}{cc}1\times 1,& 256\\ 3\times 3,& 256\\ 1\times 1,& 1024\end{array}\right]\times 6$, Mish
Non-local attention module	14 × 14	Attention × 1
Stage 5	7 × 7	$\left[\begin{array}{cc}1\times 1,& 512\\ 3\times 3,& 512\\ 1\times 1,& 2048\end{array}\right]\times 3$, Mish
Average pooling	1 × 1	7 × 7, stride 1
FC, softmax	1000-d