Few-Shot Class-Incremental Image-to-Text on DTD
55.11AccuracyCoACT
Evaluation Results
| Method | Links | |
|---|---|---|
| CoACTBackbone=ViT-B/162024.05 | 55.11 | |
| Prototype Learning2024.05 | 54.72 | |
| Linear Tuning2024.05 | 54.72 | |
| LoRA2024.05 | 54.7 | |
| PriViLege2024.05 | 54.44 | |
| CPE-CLIP2024.05 | 53.92 |