Fine-grained Image Classification on Oxford-IIIT Pets (Acc, ECE, SCE)
88.61AccuracyDynaPrompt+C-TPT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DynaPrompt+C-TPTBackbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 88.61 | 2.43 | 57 | |
| DynaPrompt+O-TPTBackbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 88.55 | 2.78 | 58 | |
| DynaPrompt+FPPBackbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 88.36 | 4.96 | 70 | |
| DynaPrompt (Paper)Backbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 88.28 | — | — | |
| C-TPTVenue=ICLR 2024, Backbone=CLIP-ViT/B16, Framework=TPT, Prompt Template=a photo of a2026.04 | 88.2 | 1.9 | 58 | |
| CLIPVenue=ICML 2021, Backbone=CLIP-ViT/B16, Framework=TPT, Prompt Template=a photo of a2026.04 | 88 | 4.37 | 68 | |
| O-TPTVenue=CVPR 2025, Backbone=CLIP-ViT/B16, Framework=TPT, Prompt Template=a photo of a2026.04 | 87.95 | 1.9 | 57 | |
| DynaPrompt (Replication)Backbone=CLIP-ViT/B16, Framework=DynaPrompt, Hard Prompt=a photo of a2026.04 | 87.71 | 5.62 | 57 | |
| FPPVenue=CVPR 2026, Backbone=CLIP-ViT/B16, Framework=TPT, Prompt Template=a photo of a2026.04 | 87.3 | 2.63 | 70 | |
| TPTVenue=NeurIPS 2022, Backbone=CLIP-ViT/B16, Framework=TPT, Prompt Template=a photo of a2026.04 | 87.1 | 5.77 | 60 |