Fine-grained Image Classification on 10-dataset Average
65.43AccuracyDynaPrompt (Paper)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DynaPrompt (Paper)Backbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 65.43 | — | — | |
| DynaPrompt+FPPBackbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 65.26 | 4.56 | 1.13 | |
| DynaPrompt (Replication)Backbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 64.22 | 13.62 | 1.43 | |
| DynaPrompt+C-TPTBackbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 63.86 | 6.89 | 1.25 | |
| DynaPrompt+O-TPTBackbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 63.35 | 6.48 | 1.26 |