Few-Shot Class-Incremental Image-to-Text on Caltech101
86.86AccuracyCoACT
Evaluation results
| Method | Links | |
|---|---|---|
| CoACTBackbone=ViT-B/162024.05 | 86.86 | |
| LoRA2024.05 | 83.87 | |
| Linear Tuning2024.05 | 83.6 | |
| PriViLege2024.05 | 83.49 | |
| Prototype Learning2024.05 | 83.47 | |
| CPE-CLIP2024.05 | 82.79 |