Table 3 Analysis of the ablation experiments made.

From: An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification

S. No

Experiment

Number of Parameters (M)

Accuracy (in %)

Precision (in %)

Recall (in %)

1

EfficientNetB4 Track

19.5

88.09

88.98

86.60

2

RIPEANet without Coordinate Attention

22.1

78.79

76.20

76.42

3

RIPEANet with Coordinate Attention

29.9

81.46

83.10

81.46

4

Proposed Network (Non-augmented training)

49

86.33

86.58

86.33

5

Proposed Hybrid Feature Aggregation Network

49

93.06

88.18

87.18

Back to article page