One Label, One Billion Faces - Usage and Consistency of Racial Categories in Computer Vision

One Label, One Billion Faces - Usage and Consistency of Racial Categories in Computer Vision

ACM FAccT Conference via YouTube Direct link

Conclusions

13 of 13

13 of 13

Conclusions

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

One Label, One Billion Faces - Usage and Consistency of Racial Categories in Computer Vision

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Face Recognition
  3. 3 Synthesis
  4. 4 Group Fairness
  5. 5 Demographic Parity
  6. 6 Fairness is based on groups.
  7. 7 Racial Categories: Badly Defined
  8. 8 Moment of Identification
  9. 9 Scenario 2
  10. 10 Classifier Ensemble
  11. 11 Cross-Dataset Generalization
  12. 12 Stereotypes
  13. 13 Conclusions

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.