Skip to main content

Table 4 3D-UCaps performance comparison for \(F_{1}\) score, Precision (Pr.), Recall (Re.) with respect to the number of classes

From: Volumetric macromolecule identification in cryo-electron tomograms using capsule networks

 

Validation

Test

 

\(F_{1}\)

Pr.

Re.

\(F_{1}\)

Pr.

Re.

Real data

PT-BG

0.93

0.95

0.91

0.74

0.77

0.71

RB-BG

0.83

0.89

0.77

0.68

0.76

0.62

PT-RB-BG

0.93

0.96

0.90

0.91

0.95

0.87

SHREC’19

4D8Q-BG

0.92

0.95

0.89

0.92

0.95

0.88

1BXN-BG

0.88

0.90

0.85

0.86

0.89

0.82

3GL1-BG\(^{\dagger }\)

0.51

0.55

0.47

0.32

0.26

0.41

4D8Q-1BXN-3GL1-BG

0.86

0.91

0.81

0.71

0.79

0.64

  1. \(^{\dagger }\)Training patch size is \(32 \times 32 \times 32\). More details is in “Case Study” section