Table 11 Runtime and memory usage comparison.

From: Collaborative representation and confidence-driven semi-supervised learning for hyperspectral image classification

Baseline

Train time (s)

Test inference (ms/forward)

Peak CPU RSS (MB)

Peak GPU allocated (MB)

Peak GPU reserved (MB)

GCN

2.74

1.76

1169.87

58.1

1000

GAT

4.29

5.245

1215.14

201.69

1000

ViT

4.59

2.999

1237.27

86.01

1000

Hybrid

5.45

3.119

1358.98

88.18

1000

Efficient

5.74

12.062

1411.21

217.74

800

Ours

1.6

1.682

1426.59

143.16

1000