List your company

Image-to-Text Retrieval on Urban-1k (Top-1 Accuracy)

94.6Top-1 AccuracyHyFL-CLIP
78.79282.8968791.104Jul 1, 2026

Evaluation results

MethodLinks
HyFL-CLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0794.6
SmartCLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0793.3
FineLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0793.2
HiMo-CLIP†Backbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0793
LongD-CLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0791.9
HyFL-CLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0791.8
TULIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0790.1
SmartCLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0790
FineLIP*Backbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0789.3
HiMo-CLIP*Backbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0789.2
TULIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0788.1
LongD-CLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0787.2
Fix-CLIPBackbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0786.8
Long-CLIP†Backbone=ViT-L-14, Evaluation Protocol=Zero-shot2026.0782.4
Fix-CLIPBackbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0780.9
Long-CLIP†Backbone=ViT-B-16, Evaluation Protocol=Zero-shot2026.0779.4