Table 1 Vessel verification results on 50,000 positive pairs and 50,000 negative pairs of vessels for the nearest neighbor and SVM classifiers by utilizing the generic and end-to-end learning-based vessel representations learned in IMO training set, which does not contain any images of the vessels in IMO test set
From: Generic and attribute-specific deep representations for maritime vessels
| Â | Representation | True positives | True negatives | False positives | False negatives | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|---|
NN | 109-dimensional output based | 44,978 | 40,198 | 9,802 | 5,022 | 85.18% | 0.82 | 0.90 |
SVM | 109-dimensional output based | 45,503 | 45,422 | 4,578 | 4,497 | 90.93% | 0.91 | 0.91 |
NN | 4144-dimensional output based | 47,305 | 41,148 | 8,852 | 2,695 | 88.45% | 0.84 | 0.95 |
SVM | 4144-dimensional output based | 46,225 | 47,744 | 2,256 | 3,775 | 93.97% | 0.95 | 0.92 |
NN | Siamese network based | 44,459 | 40,390 | 9,610 | 5,541 | 84.85% | 0.82 | 0.89 |
SVM | Siamese network based | 45,869 | 46,150 | 3,850 | 4,131 | 92.02% | 0.92 | 0.92 |