Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups
This addresses bias in gender classification for diverse racial groups, offering a mitigation strategy that improves accuracy and reduces bias, though it builds on existing methods.
The paper tackled bias in automated face-based gender classification algorithms, which show unequal accuracy for women and dark-skinned people, by proposing a strategy using generative views, structured learning, and evidential learning to improve classification accuracy and reduce bias across gender-racial groups, achieving state-of-the-art performance in evaluations.
Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people. To mitigate the bias of gender classifiers, the vision community has developed several strategies. However, the efficacy of these mitigation strategies is demonstrated for a limited number of races mostly, Caucasian and African-American. Further, these strategies often offer a trade-off between bias and classification accuracy. To further advance the state-of-the-art, we leverage the power of generative views, structured learning, and evidential learning towards mitigating gender classification bias. We demonstrate the superiority of our bias mitigation strategy in improving classification accuracy and reducing bias across gender-racial groups through extensive experimental validation, resulting in state-of-the-art performance in intra- and cross dataset evaluations.