Algorithm 1: Algorithm for CBAM attention mechanism

Input: Network intermediate volume characteristics map

Output: Attention maps

1: CAM performs a spatially informative aggregation operation on the feature map: $$\begin{array}{cc}\hfill {\mathbf{M}}_{\mathbf{c}}\left(\mathbf{F}\right)& =\sigma (MLP(AvgPool\left(\mathbf{F}\right))+(MLP(MaxPool(\mathbf{F}\left)\right))\hfill \\ & =\sigma \left({\mathbf{W}}_{\mathbf{1}}\left({\mathbf{W}}_{\mathbf{0}}\left({\mathbf{F}}_{\mathbf{a}\mathbf{v}\mathbf{g}}^{\mathbf{c}}\right)\right)+{\mathbf{W}}_{\mathbf{1}}\left({\mathbf{W}}_{\mathbf{0}}\left({\mathbf{F}}_{max}^{\mathbf{c}}\right)\right)\right)\hfill \end{array}$$

2: The channel attention map is multiplied at the pixel level with the original image: $$\begin{array}{cc}{\mathbf{F}}^{\prime }=\hfill & {\mathbf{M}}_{\mathbf{c}}\left(\mathbf{F}\right)\otimes \mathbf{F},\hfill \end{array}$$

3: SAM performs feature focus and dimensionality reduction operations on feature maps: $$\begin{array}{cc}{\mathbf{M}}_{\mathbf{s}}\left(\mathbf{F}\right)\hfill & =\sigma \left(f^{7\times 7}\left([AvgPool\left({\mathbf{F}}^{\prime }\right);MaxPool\left({\mathbf{F}}^{\prime }\right)]\right)\right)\hfill \\ \hfill & =\sigma \left(f^{7\times 7}\left(\left[{\mathbf{F}}_{\mathbf{a}\mathbf{v}\mathbf{g}}^{\mathbf{s}};{\mathbf{F}}_{max}^{\mathbf{s}}\right]\right)\right)\hfill \end{array}$$

4: Spatial Attention Maps are multiplied by the original map at the pixel level: $$\begin{array}{c}\hfill {\mathbf{F}}^{″}={\mathbf{M}}_{\mathbf{s}}\left({\mathbf{F}}^{\prime }\right)\otimes {\mathbf{F}}^{\prime }\end{array}$$

5: Output CBAM processed feature maps.