CLIP shows a robust achromatic color bias and a strong text-over-vision Stroop effect, with color-selective neurons appearing in shallow layers.
Multiviz: Towards visualizing and understanding multimodal models
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
-
Color in Visual-Language Models: CLIP deficiencies
CLIP shows a robust achromatic color bias and a strong text-over-vision Stroop effect, with color-selective neurons appearing in shallow layers.