# Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations Source: [Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:51:21.649Z Authors: Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente Ordonez Published: 2018-11-20T21:11:53.000Z ## Abstract In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that trained models significantly amplify the association of target labels with gender beyond what one would expect from biased datasets. Surprisingly, we show that even when datasets are balanced such that each label co-occurs equally with each gender, learned models amplify the association between labels and gender, as much as if data had not been balanced! To mitigate this, we adopt an adversarial approach to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network -- and provide a detailed analysis of its effectiveness. Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset (actions), show reductions in gender bias amplification while maintaining most of the accuracy of the original models. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImSitu](): Image Classification; ImSitu; Accuracy: 42.83. ## Original sources and implementation [Original paper]() [PDF]()