A Self-Supervised Few-Shot Semantic Segmentation Method Based on Multi-Task Learning and Dense Attention Computation

. 2024 Jul 31;24(15):4975. doi: 10.3390/s24154975

Algorithm 1 FSS self-supervised framework based on multi-task learning

1:
multi-task $_$ split( $I m a g e$ ):
2:
$S a l i e n c y =$ Unsupervised $_$ Saliency $_$ Detection $(I m a g e)$
3:
$S a l i e n c y 1, S a l i e n c y 2 = S p l i t (S a l i e n c y)$
4:
if $r a n d o m . r a n d o m () < a$ then
5:
$t a r g e t = S a l i e n c y$
6:
$l o s s = n n . C r o s s E n t r o p y L o s s ()$
7:
else {}
8:
$t a r g e t = S a l i e n c y 2$
9:
$l o s s = n n . C r o s s E n t r o p y L o s s (g n o r e_i n d e x = S a l i e n c y 1)$
10:
end if
11:
$q_i m a g e, t a r g e t = A u g m e n t a t i o n s (I m a g e, t a r g e t)$
12:
$s_i m a g e, s_m a s k = A u g m e n t a t i o n s (I m a g e + b, S a l i e n c y 1)$
13:
$r e s u l t = M L D A C (q_i m a g e, s_i m a g e, s_m a s k)$
14:
$l o s s = l o s s (r e s u l t, t a r g e t)$