Specifically, AA is reshaped to RC×C, and then perform a matrix multiplication between AA and the transpose of AA. Finally, a softmax layer is applied to obtain the channel attention map ∈RC×C: xji=exp(Ai⋅Aj)∑i=1Cexp(Ai⋅Aj) (2) where xji measures the ith channel’s ...
Finally, we apply a matrix multiplication to 𝛼[𝛼𝑡,𝛼𝑠]α[αt,αs] and [𝑋𝑠,𝑋𝑡]𝑇[Xs,Xt]T to obtain the output of CSTA block (denoted as Y), whose dimension is the same as input. In summary, based on the DTP network structure, the MA module can make the...
Finally, we apply a matrix multiplication to 𝛼[𝛼𝑡,𝛼𝑠]α[αt,αs] and [𝑋𝑠,𝑋𝑡]𝑇[Xs,Xt]T to obtain the output of CSTA block (denoted as Y), whose dimension is the same as input. In summary, based on the DTP network structure, the MA module can make the...