Table 11 Base CUB_200_2011 classification results
From: Multimodal prototype fusion network for paper-cut image classification
Methods | Type | Training | n-shot accuracy (%) | |
|---|---|---|---|---|
5-shot | 16-shot | |||
COOP | Prompt learning | Yes | 72.05 | 80.56 |
CoCoOp | Prompt learning | Yes | 73.10 | 74.10 |
CLIP zero-shot | Contrastive learning | No | 60.33 | 60.33 |
CLIP-linear | Deep learning | Yes | 58.05 | 68.89 |
Prototypical network | Metric learning | No | 71.05 | 77.91 |
Matching network | Metric learning | No | 60.27 | 69.24 |
AMPFN | Metric learning | Yes | 73.56 | 80.58 |
IMPFN | Metric learning | No | 75.28 | 77.22 |
