Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Image-to-Text Retrieval on Urban-1k (Top-1 Accuracy)
Loading...
94.6
Top-1 Accuracy
HyFL-CLIP
78.792
82.896
87
91.104
Jul 1, 2026
Top-1 Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
HyFL-CLIP
Backbone=ViT-L-14, Eva...
2026.07
94.6
SmartCLIP
Backbone=ViT-L-14, Eva...
2026.07
93.3
FineLIP
Backbone=ViT-L-14, Eva...
2026.07
93.2
HiMo-CLIP†
Backbone=ViT-L-14, Eva...
2026.07
93
LongD-CLIP
Backbone=ViT-L-14, Eva...
2026.07
91.9
HyFL-CLIP
Backbone=ViT-B-16, Eva...
2026.07
91.8
TULIP
Backbone=ViT-L-14, Eva...
2026.07
90.1
SmartCLIP
Backbone=ViT-B-16, Eva...
2026.07
90
FineLIP*
Backbone=ViT-B-16, Eva...
2026.07
89.3
HiMo-CLIP*
Backbone=ViT-B-16, Eva...
2026.07
89.2
TULIP
Backbone=ViT-B-16, Eva...
2026.07
88.1
LongD-CLIP
Backbone=ViT-B-16, Eva...
2026.07
87.2
Fix-CLIP
Backbone=ViT-L-14, Eva...
2026.07
86.8
Long-CLIP†
Backbone=ViT-L-14, Eva...
2026.07
82.4
Fix-CLIP
Backbone=ViT-B-16, Eva...
2026.07
80.9
Long-CLIP†
Backbone=ViT-B-16, Eva...
2026.07
79.4
Feedback
Search any
task
Search any
task