On a new benchmark of odd-one-out images, state-of-the-art vision-language models, including GPT-4o, often fail to identify which low-level feature makes the odd object stand out.
Turning visual search time on its head
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
-
Vision-Language Models Can't See the Obvious
On a new benchmark of odd-one-out images, state-of-the-art vision-language models, including GPT-4o, often fail to identify which low-level feature makes the odd object stand out.