Table 4 Comparison of VQRESNET50_10 model with classical DLMs.

From: Variational quantum enhanced deep transfer learning for small underwater aqua species image classification

Model

Training parameter

FLOPs

Inference time (s)

Validation accuracy (%)

ResNet50

23,805,829

47,611,658

1.19

95.6

MobileNetV2

24,31,301

4,862,602

0.95

85.69

InceptionResNetV2

54,481,893

108,963,786

3.499

84.77

DenseNet201

18,34,781

366,955,62

3.58

92.48

ISONet

3,278,371

65, 56,742

2.609

94.40

VQ ResNet50_10

18,337

36,674

0.295

99.08

Back to article page