Facemesh Model Card

MediaPipe Face Mesh

These are the Model Card, the Research, and the Research Blog

• Date created: 2018

• Size: Not stated

• How the data was collected: “All dataset images were captured on a diverse set of smartphone cameras, both front- and back-facing. All images were captured in a real-world environment with different light, noise and motion conditions via an AR (Augmented Reality) application.”

• Bias:

  • According to the model card, the models are stated to perform “well” across most groups.

    • Categories of evaluation:
      • 17 geographic subregions
      • 6 skin tones
      • Male / Female (gender)
    • Evaluation results:
      • Subregions: Difference in confidence between best and worst performing regions of 0.9% for the tracking mode and 1.56% for the reacquisition mode.
      • Genders: Difference in confidence is 0.02% for the tracking mode and 0.1% for the reacquisition mode.
      • Skin tones: Difference in confidence is 0.24% for tracking mode and 1.12% for the reacquisition mode.

  • There is no additional research conducted to evaluate the fairness.

  • There is no additional research conducted to evaluate the fairness.

MediaPipe Attention Mesh

This is the Model Card

• Date created: 2020

• Size: 30K (assuming)

• How the data was collected: “All dataset images were captured on a diverse set of smartphone cameras, both front- and back-facing. All images were captured in a real-world environment with different light, noise and motion conditions via an AR (Augmented Reality) application.”

• Bias:

  • According to the model card, the models are stated to perform “well” across most groups.

    • Categories of evaluation:
      • 17 geographic subregions
      • 6 skin tones
      • Male / Female (gender)
    • Evaluation results:
      • Subregions: Difference in confidence between best and worst performing regions of 1.22% for the tracking mode and 1.27% for the reacquisition mode.
      • Gender: Difference in confidence is 0.01% for the tracking mode and 0.03% for the reacquisition mode.
      • Skin tones: Difference in confidence is 0.54% for tracking mode and 0.88% for the reacquisition mode.

• Potential bias:

  • Potential biases in the model which may result in drastic confidence differences if evaluated: May have difficulty with facial accessories like glasses or cultural headwear.

Please submit any feedback/information you belive would be useful regarding this model here.