Zero-shot Classification on Food 101
95.08Accuracy (Zero-shot)CLIPFT + A
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CLIPFT + ABackbone=ViT-B/16, Prompting Strategy=LLM Attributes, Training Samples per Class=16, Training Protocol=Fine-tuned2024.01 | 95.08 | — | — | — | — | |
| CLIP + ABackbone=ViT-B/16, Prompting Strategy=LLM Attributes, Training Samples per Class=0, Training Protocol=Zero-shot (Pre-trained)2024.01 | 93.72 | — | — | — | — | |
| CLIPBackbone=ViT-B/16, Prompting Strategy=Standard, Training Samples per Class=0, Training Protocol=Zero-shot (Pre-trained)2024.01 | 92.49 | — | — | — | — | |
| CLIP-A-selfBackbone=ViT-B/16, Prompting Strategy=GPT Attributes, Training Samples per Class=16, Training Protocol=Adapter Tuning2024.01 | 91.2 | — | — | — | — | |
| BiFTABackbone=ViT-B/16, Zero-shot=true2026.01 | 90.11 | — | — | — | — | |
| WCABackbone=ViT-B/16, Zero-shot=true2026.01 | 89.99 | — | — | — | — | |
| CLIP-PZSLq=0.12026.03 | 89.46 | — | — | 80.24 | — | |
| WaffleBackbone=ViT-B/16, Zero-shot=true2026.01 | 89.06 | — | — | — | — | |
| CuPLBackbone=ViT-B/16, Zero-shot=true2026.01 | 88.98 | — | — | — | — | |
| CLIP-DBackbone=ViT-B/16, Zero-shot=true2026.01 | 88.85 | — | — | — | — | |
| CLIP-EBackbone=ViT-B/16, Zero-shot=true2026.01 | 88.83 | — | — | — | — | |
| CLIP-PZSLq=0.32026.03 | 88.8 | — | — | 80.17 | — | |
| CLIPBackbone=ViT-B/16, Zero-shot=true2026.01 | 88.4 | — | — | — | — | |
| CLIP-PZSLq=0.52026.03 | 87.58 | — | — | 80.07 | — | |
| CLIPq=0.12026.03 | 81.13 | — | — | 79.29 | — | |
| CLIPq=0.32026.03 | 81.13 | — | — | 79.29 | — | |
| CLIPq=0.52026.03 | 81.13 | — | — | 79.29 | — | |
| CALIPq=0.12026.03 | 79.77 | — | — | 78.03 | — | |
| CALIPq=0.32026.03 | 79.77 | — | — | 78.03 | — | |
| CALIPq=0.52026.03 | 79.77 | — | — | 78.03 | — | |
| Anti-Adv2026.01 | — | 83.9 | 29.3 | — | — | |
| C-PGCVariant=RN101-COCO2026.05 | — | — | — | — | 37.8 | |
| C-PGCVariant=ViT-B/16-COCO2026.05 | — | — | — | — | 65.1 | |
| CLIP2026.01 | — | 84.8 | 0 | — | — | |
| CSR2026.01 | — | 81.9 | 80.7 | — | — | |
| DarkLLMVariant=Ensemble2026.05 | — | — | — | — | 83.5 | |
| ETUVariant=RN50-Flickr2026.05 | — | — | — | — | 32.7 | |
| ETUVariant=ViT-B/16-Flickr2026.05 | — | — | — | — | 67.8 | |
| FARE2026.01 | — | 47 | 44.5 | — | — | |
| GD-UAPVariant=Seg2026.05 | — | — | — | — | 36.1 | |
| GD-UAPVariant=CLS2026.05 | — | — | — | — | 55.2 | |
| HD2026.01 | — | 86 | 1.1 | — | — | |
| LPF2026.01 | — | 79.6 | 38.6 | — | — | |
| Meta-UAPVariant=Ensemble2026.05 | — | — | — | — | 59.8 | |
| Meta-UAPVariant=Ensemble-Meta2026.05 | — | — | — | — | 53.3 | |
| R-TPT2026.01 | — | 86.6 | 68.9 | — | — | |
| TeCoA2026.01 | — | 30.6 | 29.2 | — | — | |
| TRM-UAPVariant=GoogleNet2026.05 | — | — | — | — | 60.7 | |
| TRM-UAPVariant=RN1522026.05 | — | — | — | — | 54.4 | |
| TTC2026.01 | — | 57.5 | 33.2 | — | — | |
| TTE2026.01 | — | 85.3 | 24.8 | — | — | |
| X-TransferVariant=Vanilla2026.05 | — | — | — | — | 60.6 | |
| X-TransferVariant=Base2026.05 | — | — | — | — | 83.6 |