Table 6 Classification accuracy of tiered-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

Relation net

Conv

54.31

71.22

MAML

Conv

51.83

70.83

Proto net

Conv

53.48

72.64

TPN

Conv

59.61

72.58

EGNN

Conv

–

80.15

CA-EGNN

CA-PFE

61.11

80.61

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