Table 6 Analysis of the proposed work in comparison to current studies that have utilized the Makerere university AI lab’s cassava leaf disease dataset.

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

S. No

Source

Model

Accuracy

(in %)

1

Tewari et al.34

Lightweight Modified Attention-based Network

75.00

2

Methil et al.15

Transfer Learning EfficientNet-B4

85.64

3

Singh et al.35

InceptionResNetV2

87.86

4

Maryum et al.29

Transfer Learning EfficientNet-B4

89.09

5

Chen et al.36

Transfer Learning ResNest-59

89.70

6

Zhang et al.37

SimCLR

91.59

7

Vijayalata et al.38

Transfer Learning EfficientNet-B0

92.60

8

Proposed Network

Hybrid Feature Aggregation Network

93.06