Few-shot Classification on Caltech101 16-shot (test)
92.07Accuracy (Sym 0.125)NA-MVP
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| NA-MVPImage Encoder=ResNet-50, Text Encoder=63M-parameter Transformer, Training Shots=16, Training Epochs=502026.03 | 92.07 | 92.1 | 91.6 | 91.3 | 90.07 | 89.37 | 91.47 | 89.53 | |
| GCEImage Encoder=ResNet-50, Text Encoder=63M-parameter Transformer, Training Shots=16, Training Epochs=502026.03 | 92 | 90.9 | 90.8 | 89.3 | 86.7 | 79.03 | 91.2 | 85.8 | |
| NLPromptImage Encoder=ResNet-50, Text Encoder=63M-parameter Transformer, Training Shots=16, Training Epochs=502026.03 | 91.73 | 91.13 | 90.77 | 89.93 | 88.3 | 86.7 | 91.17 | 89.27 | |
| JoAPRImage Encoder=ResNet-50, Text Encoder=63M-parameter Transformer, Training Shots=16, Training Epochs=502026.03 | 88.32 | 87.85 | 87 | 87.03 | 84.55 | 80.15 | 82.79 | 69.02 | |
| CoOpImage Encoder=ResNet-50, Text Encoder=63M-parameter Transformer, Training Shots=16, Training Epochs=502026.03 | 86.43 | 81.03 | 76.73 | 70.9 | 61.33 | 46.9 | 75.23 | 49.43 |