Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cross-modal Retrieval (Image to Text) on iNaturalist Species-level Retrieval (seen)
Loading...
86.3
Top-1 Accuracy
BioVITA
-3.4416
19.8567
43.155
66.4533
Mar 25, 2026
Top-1 Accuracy
Top-5 Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
Top-5 Accuracy
BioVITA
Training Stage=Stage2
2026.03
86.3
96
BioCLIP 2
2026.03
65.1
80.5
BioVITA
Training Stage=Stage1
2026.03
65.1
80.5
ImageBind
2026.03
59.5
81.4
TaxaBind
2026.03
56.9
80
CLIP
2026.03
50.9
65.1
Random
2026.03
0.01
0.05
Feedback
Search any
task
Search any
task
