SigLIP SO/14 + PrefixedIter Decoder (FT2)

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision1 result

Zero-Shot Image ClassificationonOVIC Datasets (World-H)
Prediction Score (mean of 3)· 2024-07-15
87.49
SOTA
Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion arXiv:2407.11211