Few-Shot Class-Incremental Image-to-Text on MiniImageNet
95.34AccuracyCoACT
Evaluation Results
| Method | Links | |
|---|---|---|
| CoACTBackbone=ViT-B/162024.05 | 95.34 | |
| Linear Tuning2024.05 | 95.32 | |
| LoRA2024.05 | 95.32 | |
| Prototype Learning2024.05 | 95.31 | |
| PriViLege2024.05 | 95.04 | |
| CPE-CLIP2024.05 | 94.57 |