Table 7 Model efficiency comparison on Deepship, using single RTX 3090.

From: Hybrid local-global representation learning with stochastic Gaussian classification for underwater acoustic target recognition

Model

params(MB)

Gflops

Accuracy

DNN

67.24

1.08

73.11

Inception

48.46

260.67

76.16

Residual

23.51

169.40

76.98

AudioMAE

85.26

349.68

76.66

SSAST

85.26

827.54

77.70

SSLMM

86.68

633.62

80.22

MIXUP

86.68

1900.86

86.23

Ours

87.74

833.31

88.48

  1. Bold values denotes the best performance for this metric.
Back to article page