Using a controllable synthetic dataset, the authors show that common data properties, especially saliency bias, prevent CLIP models from learning object-attribute binding, and that fixing the data achieves near-perfect binding.
IEEE Transactions on Image Processing22(1), 55–69 (2012)
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
-
Common Data Properties Limit Object-Attribute Binding in CLIP
Using a controllable synthetic dataset, the authors show that common data properties, especially saliency bias, prevent CLIP models from learning object-attribute binding, and that fixing the data achieves near-perfect binding.