Algorithm 1. Derivation of new source feature space

Input: (1) Offline sample $D_{of}$; (2) Target domain $D_T$; (3) The number of instances $n_T$;

Output: Source domain $D_S$

1. $D_S=\left[\right]$

2. for $l=1,2,\dots ,L$ do

3.   for $m=1,2,\dots ,n_T$ do

4.      for $i=1,2,\dots ,n_{of}$ do

5.         Compute co-occurrence $C\left(m,i\right)$ using Equation (2)

6.      end for

7.     Obtain the co-occurrence vector of the mth target sample

8.    end for

9. end for

10. for $i=1,2,\dots ,n_S$ do

11.   Find $i,m$ $s.t$ $C\left(m,i\right)=\max C_{mi}^p$

12.  $x_{of}^p=x_S^{p^{/}},y_{of}^p=y_S^{p^{/}}$

13.  $D_S=\left\{\left(x_S^{p^{/}},y_S^{p^{/}}\right)\right\}$

14. end for

15. return $D_S$