Table 5 Classification accuracy of mini-ImageNet dataset for different classification tasks.

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

Model

Backbone network

5-way 1-shot

5-way 5-shot

Matching net

Conv

43.67

54.71

Relation net

Conv

50.21

64.65

MAML

Conv

49.56

56.17

Proto net

Conv

49.26

64.78

Dynamic

Conv

56.13

72.01

GNN

Conv

50.34

65.98

TPN

Conv

55.54

69.97

EGNN

Conv

–

75.78

CA-EGNN

CA-PFE

58.34

77.39

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