Skip to main content

Table 8 The comparison of accuracy of the CCNNet1.5X embedding different attentions

From: CCNNet: a novel lightweight convolutional neural network and its application in traditional Chinese medicine recognition

Setting

Parameters/M

M-Adds/M

top-1Acc (%)

CCNNet + MDCA

2.2

366

73.2

CCNNet + SE

2.2

366

72.7

CCNNet + CBAM

2.2

366

72.3

CCNNet + CA

2.35

381

73.3

CCNNet + SimAM

2.2

366

71.8