Table 5 Performance comparison of DNN models vs. the proposed model.

From: Hybrid pre trained model based feature extraction for enhanced indoor scene classification in federated learning environments

Models

Accuracy

(%)

Validation Accuracy (%)

Loss

(0–1)

Validation Loss

(0–1)

DenseNet201

92.14

72.92

0.23

1.54

InceptionResNetV2

83.9

59.36

0.52

2.1

MobileNetV2

74.08

51.93

0.83

2.22

ResNet152V2

85.65

60.15

0.48

2.07

VGG16

98.79

87.47

0.04

0.8

VGG19

98.37

85.21

0.05

1.08

MultiData

99.99

99.93

0

0.01

Back to article page