SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation

Algorithm 1

The proposed fusion nonmaximum suppression algorithm (Fusion NMS).

Input: Mask set , category set , confidence set

Output: updated , and

[1] Sort , and according to the value in from large to small;

[2] Initialize the number of predictions

[3] fordo

[4]   fordo

[5]     ifthen

[6]       Calculate ;

[7]       ifthen

[8]          Fuse the prediction: ;

[9]          Remove the prediction: ;

[10]          ;

[11]       end if

[12]     end if

[13]   end for

[14] end for

[15] return Updated , and