Table 3 Classification accuracy of mini-ImageNet dataset under different transduction settings.

From: Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification

Model

Trans.

5-way 5-shot

Matching networks

NO

55.30

Reptile

NO

62.74

Prototypical net

NO

65.77

GNN

NO

66.41

EGNN

NO

66.85

CA-EGNN

NO

68.02

MAML

BN

63.11

Reptile

BN

65.99

Relation Net

BN

67.07

MAML

YES

66.19

TPN

YES

69.43

TPN(Higher K)

YES

69.86

EGNN

YES

76.37

CA-EGNN

YES

77.39

  1. Significant values are in bold.
Back to article page