Table 7 Ablation study of DMSCA components on CIFAR-100 with ResNet-18.

From: DMSCA: dynamic multi-scale channel-spatial attention for enhanced feature representation in convolutional neural networks

Serial Number

Model Configuration

Top1-Acc

ΔAcc

(vs. Baseline)

ΔAcc

(vs. Prev)

Params (M)

FLOPs (G)

1

ResNet-18

75.32 ± 0.21

-

-

11.17

1.81

2

ResNet-18 + GCE

75.81 ± 0.19

+ 0.49

+ 0.49

11.20

1.81

3

ResNet-18 + TCA(τ = 1)

76.15 ± 0.20

+ 0.83

+ 0.34

11.21

1.81

4

ResNet-18 + GCE + TCA (τ = dynamic, from DII)

76.32 ± 0.18

+ 1.00

+ 0.17

11.21

1.81

5

ResNet-18 + MSCE (K= {3,5,7})

76.05 ± 0.22

+ 0.73

-

11.23

1.82

6

ResNet-18 + GCE + TCA(τ = dyn) +MSCE (K= {3,5,7})

76.68 ± 0.19

+ 1.36

+ 0.36

11.26

1.82

7

ResNet-18 + GCE + TCA(τ = dyn) +MSCE + DII

76.95 ± 0.17

+ 1.63

+ 0.27

11.27

1.82

8

ResNet-18 + GCE + TCA (τ = dyn) +MSCE + DII+DFF

77.08 ± 0.18

+ 1.76

+ 0.13

11.27

1.82

9

ResNet-18 + DMSCA(Full)

77.13 ± 0.16

+ 1.81

+ 0.05

11.28

1.82

  1. Note: ΔAcc (vs. Prev) denotes accuracy change from previous configuration. Values are mean ± SD from five runs.