Table 12.

Effect of attention weighted blocks with different pooling operations at the first and the last transition layers

Method			DR (QK)	p value
First transition layer	Attention	Global pooling layer
Max	–	Average	$0.781\pm 0.003$	0.0006
Max	CBAM	Average	$0.788\pm 0.008$	0.4051
Max	$A^2$	Average	$0.791\pm 0.005$	–
GM	–	GM	$0.785\pm 0.006$	0.0219
GM	CBAM	GM	$0.787\pm 0.006$	0.0961
GM	$A^2$	GM	$\mathbf{0.793}\pm \mathbf{0.006}$	–

The top scores are highlighed in bold