Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion

Benchmark Model Rank Results
open-vocabulary-image-classification-on-ovic-datasets-wiki-hDFN-5B H/14-378 + PrefixedIter Decoder (FT0)#1Overall Score: 78.21Prediction Score: 79.18Top 1 Accuracy: 77.10
open-vocabulary-image-classification-on-ovic-datasets-wiki-hDFN-5B H/14-378 + PrefixedIter Decoder (FT2)#2Overall Score: 79.02Prediction Score: 80.13Top 1 Accuracy: 77.05
open-vocabulary-image-classification-on-ovic-datasets-wiki-hSigLIP B/16 + PrefixedIter Decoder (FT2)#3Prediction Score (mean of 3): 72.03
open-vocabulary-image-classification-on-ovic-datasets-world-hSigLIP SO/14 + PrefixedIter Decoder (FT2)#1Prediction Score (mean of 3): 87.49
open-vocabulary-image-classification-on-ovic-datasets-world-hDFN-5B H/14-378 + PrefixedIter Decoder (FT2)#2Prediction Score (mean of 3): 87.08Overall Score: 87.13…
open-vocabulary-image-classification-on-ovic-datasets-world-hDFN-5B H/14-378 + PrefixedIter Decoder (FT0)#3Prediction Score (mean of 3): 86.41Overall Score: 87.90…
image-classification-on-imagenetDFN-5B H/14-378 + PrefixedIter Decoder#61Top 1 Accuracy: 88.21%
image-classification-on-imagenetSigLIP B/16 + PrefixedIter Decoder#454Top 1 Accuracy: 83.46%