Image-to-Text Retrieval on Urban-1k (Top-1 Accuracy)
94.6Top-1 AccuracyHyFL-CLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| HyFL-CLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 94.6 | |
| SmartCLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 93.3 | |
| FineLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 93.2 | |
| HiMo-CLIP†Backbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 93 | |
| LongD-CLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 91.9 | |
| HyFL-CLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 91.8 | |
| TULIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 90.1 | |
| SmartCLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 90 | |
| FineLIP*Backbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 89.3 | |
| HiMo-CLIP*Backbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 89.2 | |
| TULIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 88.1 | |
| LongD-CLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 87.2 | |
| Fix-CLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 86.8 | |
| Long-CLIP†Backbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.07 | 82.4 | |
| Fix-CLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 80.9 | |
| Long-CLIP†Backbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.07 | 79.4 |