Whitening CLIP embeddings makes their squared norm a likelihood-like score that ranks images and captions by how typical they are under a Gaussian approximation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Whitened CLIP as a Likelihood Surrogate of Images and Captions
Whitening CLIP embeddings makes their squared norm a likelihood-like score that ranks images and captions by how typical they are under a Gaussian approximation.