Blind text-only likelihood models match or exceed CLIP on many compositionality benchmarks because positives and negatives differ systematically in length, plausibility, or image style.
Image captioners are scalable vision learners too.Advances in Neural Infor- mation Processing Systems, 36, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks
Blind text-only likelihood models match or exceed CLIP on many compositionality benchmarks because positives and negatives differ systematically in length, plausibility, or image style.