Skip to main content
Account

Table 4 Ablation study of each module

From: Transferable adversarial masked self-distillation for unsupervised domain adaptation

\({{\mathcal {L}}_{\textrm{cls}}}({x^s},{y^s})\)

\({{\mathcal {L}}_{\textrm{adv}}}({x^s},{x^t})\)

\({{\mathcal {L}}_{{\text {self-KD}}}}({x^t};\theta )\)

\({{\mathcal {L}}_{{\text {MIM}}}}({x^t};\theta )\)

\({{\mathcal {L}}_{\textrm{patch}}}({x^s},{x^t})\)

\(I({p^t};{x^t})\)

\(\rightarrow \) W

\(\rightarrow \) W

\(\rightarrow \) D

\(\rightarrow \) D

\(\rightarrow \) A

\(\rightarrow \) A

Avg

\(\checkmark \)

     

89.18

98.87

100

88.76

80.09

79.77

89.45

\(\checkmark \)

\(\checkmark \)

    

90.12

98.89

100

90.45

83.43

83.23

91.02

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

   

93.14

98.93

100

93.32

84.63

85.13

92.53

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

  

95.34

99.03

100

94.14

84.93

85.67

93.19

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

 

95.44

99.01

100

94.69

85.05

85.96

93.36

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

\(\checkmark \)

96.48

99.5

100

96.99

85.87

86.26

94.18

\({{\mathcal {L}}_{\textrm{TAMS}}}\) with traditional self-attention in ViT encoder

93.52

98.79

100

94.19

84.33

85.79

92.77

\({{\mathcal {L}}_{\textrm{TAMS}}}\) with the cross-attention mechanism in ViT encoder

95.49

99.13

100

95.82

85.28

85.98

93.62

\({{\mathcal {L}}_{\textrm{TAMS}}}\) with the weighted cross-attention mechanism (Eq. (6)) in ViT encoder

96.48

99.5

100

96.99

85.87

86.26

94.18

  1. The best results have been shown in bold face