Kurtis Evan David, Qiang Liu, Ruth Fong

@article{david2020debiasing,
      title={Debiasing Convolutional Neural Networks via Meta Orthogonalization},
      author={Kurtis Evan David and Qiang Liu and Ruth Fong},
      year={2020},
      journal={arXiv preprint arXiv:2011.07453},
}

This is the official implementation of Meta Orthogonalization in PyTorch. Our main idea is to debias convolutional networks by making downstream concepts be orthogonal to a learned bias direction. This is directly inspired by similar methods in NLP by Bolukbasi et al. (2016).

To successfully run the code in this repo, make sure you have the following libraries installed:

• PyTorch 1.5.0 (CUDA 10.1)
• higher
• bam

We would like to thank Tianlu Wang for collaborating and providing more details with adversarial debiasing and their models. Please also cite their paper if you use this codebase for COCO, as we use theirs provided here.

If you have any questions, please contact us through kurtis.e.david(at)gmail.com.