Corpus ID: 53720036

Adversarial Removal of Gender from Deep Image Representations

@article{Wang2018AdversarialRO,
  title={Adversarial Removal of Gender from Deep Image Representations},
  author={Tianlu Wang and Jieyu Zhao and Mark Yatskar and Kai-Wei Chang and Vicente Ordonez},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.08489}
}
  • Tianlu Wang, Jieyu Zhao, +2 authors Vicente Ordonez
  • Published 2018
  • Computer Science
  • ArXiv
  • In this work we analyze visual recognition tasks such as object and action recognition, and demonstrate the extent to which these tasks are correlated with features corresponding to a protected variable such as gender. [...] Key Method To address this, we use adversarial training to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network. Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset (actions), show reductions in…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 11 CITATIONS

    Demoting Racial Bias in Hate Speech Detection

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    Domain-Adversarial Training of Neural Networks

    VIEW 1 EXCERPT

    What do Deep Networks Like to See?

    VIEW 1 EXCERPT

    Deep Residual Learning for Image Recognition

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Exploring Disentangled Feature Representation Beyond Face Identification