Analysis of contrastive learning with unsupervised and supervised learning approaches.
| Models | NW-UCLA | Part I | Part II | NTU |
|---|---|---|---|---|
| Linear evaluation | ||||
| Mean feature | 61.5 | 68.3 | 26.5 | 39.6 |
| Attention feature | 65.8 | 68.5 | 26.7 | 40.4 |
| Fine-tuning | ||||
| Mean feature | 81.4 | 86.3 | 45.5 | 73.6 |
| Attention feature | 83.3 | 86.3 | 46.6 | 74.0 |
| Models | NW-UCLA | Part I | Part II | NTU |
|---|---|---|---|---|
| Mean feature | 61.5 | 68.3 | 26.5 | 39.6 |
| Attention feature | ||||
| Mean feature | 81.4 | 86.3 | 45.5 | 73.6 |
| Attention feature |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.