where \(l\) indicates the number of FC layers. Constants \(\lambda _i\)\(i=1,2,...,l\) are the weights that balance the contribution of FC layers, which are set to 1 here. The squared matrix Frobenius norm is denoted as \({\left\| \right\|_F^2}\). The dimension of the \(ith\) FC layer is indicated by \({d_i}\). The feature covariance matrices of source and target domains, \({{\rm{C}}_s}\) and \({{\rm{C}}_t}\), respectively, can be calculated by: