Corpus ID: 211096751

Machines Learn Appearance Bias in Face Recognition

@article{Steed2020MachinesLA,
  title={Machines Learn Appearance Bias in Face Recognition},
  author={Ryan Steed and Aylin Caliskan},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.05636}
}
  • Ryan Steed, Aylin Caliskan
  • Published in ArXiv 2020
  • Computer Science
  • We seek to determine whether state-of-the-art, black box face recognition techniques can learn first-impression appearance bias from human annotations. With FaceNet, a popular face recognition architecture, we train a transfer learning model on human subjects' first impressions of personality traits in other faces. We measure the extent to which this appearance bias is embedded and benchmark learning performance for six different perceived traits. In particular, we find that our model is better… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    First impressions

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    The functional basis of face evaluation.

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    A face-scanning algorithm increasingly decides whether you deserve the job

    • Drew Harwell
    • 2019
    VIEW 2 EXCERPTS

    Explicit Bias Discovery in Visual Question Answering Models

    VIEW 1 EXCERPT

    HUMAN DECISIONS AND MACHINE PREDICTIONS.

    VIEW 1 EXCERPT

    Design of an explainable machine learning challenge for video interviews

    VIEW 2 EXCERPTS