Improving Fairness in Image Classification via Sketching

Abstract

Fairness is a fundamental requirement for trustworthy and human-centered Artificial Intelligence (AI) system. However, deep neural networks (DNNs) tend to make unfair predictions when the training data are collected from different sub-populations with different attributes (i.e. color, sex, age), leading to biased DNN predictions. We notice that such a troubling phenomenon is often caused by data itself, which means that bias information is encoded to the DNN along with the useful information (i.e. class information, semantic information). Therefore, we propose to use sketching to handle this phenomenon. Without losing the utility of data, we explore the image-to-sketching methods that can maintain useful semantic information for the target classification while filtering out the useless bias information. In addition, we design a fair loss to further improve the model fairness. We evaluate our method through extensive experiments on both general scene dataset and medical scene dataset. Our results show that the desired image-tosketching method improves model fairness and achieves satisfactory results among state-of-the-art (SOTA).

FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification

“…Pre-Processing. Pre-processing methods focus on the quality of the training dataset, by organizing fair datasets via datasets combination [22], using generative adversarial networks [13] or sketching model [28] to generate extra images, or directly applying resampling strategies to balance train set [20]. However, this category of methods needs huge effort due to the preciousness of medical data.…”