Table 7 Effect of augmentation during fine-tuning for differently pre-trained embedding models
From: Automated classification of polyps using deep learning architectures and few-shot learning
Model | Augm. | Acc | Pre | Rec | F1 |
|---|---|---|---|---|---|
DTD | N | 80.73 (± 8.48) | 82.05 (± 8.74) | 80.73 (± 8.48) | 80.5 (± 8.2) |
|  | Y | 81.34 (± 8.74) | 81.52 (± 8.39) | 81.34 (± 8.74) | 81.0 (± 8.6) |
self-sv. | N | 74.03 (± 8.97) | 76.13 (± 8.49) | 74.03 (± 8.97) | 75.0 (± 8.1) |
|  | Y | 75.04 (± 8.59) | 75.24 (± 8.38) | 75.04 (± 8.59) | 75.1 (± 8.3) |