Few-Shot Class-Incremental Image-to-Text on Stanford Cars
24.4AccuracyCoACT
Evaluation Results
| Method | Links | |
|---|---|---|
| CoACTBackbone=ViT-B/162024.05 | 24.4 | |
| Linear Tuning2024.05 | 18.96 | |
| LoRA2024.05 | 18.94 | |
| Prototype Learning2024.05 | 18.9 | |
| PriViLege2024.05 | 18.67 | |
| CPE-CLIP2024.05 | 18.51 |