Matched sample selection with GANs for mitigating attribute confounding

Understand

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society.

• However, significant correlations between attributes in benchmark datasets make it difficult to separate algorithmic bias from dataset bias.
• To mitigate such attribute confounding during bias analysis, we propose a matching approach that selects a subset of images from the full dataset with balanced attribute distributions across protected attributes.
• Our matching approach first projects real images onto a generative adversarial network (GAN)'s latent space in a manner that preserves semantic attributes.