Login / Signup

A set of distinct facial traits learned by machines is not predictive of appearance bias in the wild.

Ryan SteedAylin Caliskan
Published in: AI Ethics (2021)
Keyphrases
  • facial expressions
  • neural network
  • machine learning
  • feature selection
  • scheduling problem
  • small number
  • input image
  • human faces
  • appearance model
  • facial images
  • active shape