-
[pdf]
[supp]
[arXiv]
[code]
[bibtex]@InProceedings{E_Rosa_2022_ACCV, author = {E Rosa, Nicholas and Drummond, Tom and Harandi, Mehrtash}, title = {A Differentiable Distance Approximation for Fairer Image Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {212-228} }
A Differentiable Distance Approximation for Fairer Image Classification
Abstract
Naively trained AI models can be heavily biased. This can
be particularly problematic when the biases involve legally or morally
protected attributes such as ethnic background, age or gender. Existing
solutions to this problem come at the cost of extra computation, unstable
adversarial optimisation or have losses on the feature space structure that
are disconnected from fairness measures and only loosely generalise to
fairness. In this work we propose a differentiable approximation of the
variance of demographics, a metric that can be used to measure the
bias, or unfairness, in an AI model. Our approximation can be optimised
alongside the regular training objective which eliminates the need for
any extra models during training and directly improves the fairness of
the regularised models. We demonstrate that our approach improves the
fairness of AI models in varied task and dataset scenarios, whilst still
maintaining a high level of classification accuracy. Code is available at
https://bitbucket.org/nelliottrosa/base_fairness.
Related Material