Filtering face recognition test data so male and female images share specific non-demographic attributes such as hairstyle and facial hair makes measured gender accuracy gaps nearly disappear, but the causal interpretation is not supported.
Emerging from ai utopia,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes
Filtering face recognition test data so male and female images share specific non-demographic attributes such as hairstyle and facial hair makes measured gender accuracy gaps nearly disappear, but the causal interpretation is not supported.