2026-04-16T11:32:36Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00209802 2025-01-19T18:23:07Z 1164:4619:10416:10532

Counterfactual Image Generation using GAN for Fairness Counterfactual Image Generation using GAN for Fairness Koki, Wataoka Takashi, Matsubara Kuniaki, Uehara Koki, Wataoka Takashi, Matsubara Kuniaki, Uehara セッション1-1 Computer vision systems have made significant improvements and been used in a variety of situations. For a practical use, we need to prevent the systems from making unfair decisions for certain individuals. In this sense, the systems have to eliminate the difference between decision makings on the real world and the counterfactual world where users would have different sensitive attributes (e.g., gender and race). In this study, we propose a framework for counterfactual image generation named Causality with Unobserved Variables using Generative Adversarial Networks (CUV-GAN). CUV-GAN can generate counterfactual images as the results of the intervention in the images' attributes and improve the fairness of an image classifier by being trained with generated images as data augmentation. Computer vision systems have made significant improvements and been used in a variety of situations. For a practical use, we need to prevent the systems from making unfair decisions for certain individuals. In this sense, the systems have to eliminate the difference between decision makings on the real world and the counterfactual world where users would have different sensitive attributes (e.g., gender and race). In this study, we propose a framework for counterfactual image generation named Causality with Unobserved Variables using Generative Adversarial Networks (CUV-GAN). CUV-GAN can generate counterfactual images as the results of the intervention in the images' attributes and improve the fairness of an image classifier by being trained with generated images as data augmentation. technical report 情報処理学会 2021-02-25 application/pdf 研究報告コンピュータビジョンとイメージメディア（CVIM） 4 2021-CVIM-225 1 7 2188-8701 AA11131797 https://ipsj.ixsq.nii.ac.jp/record/209802/files/IPSJ-CVIM21225004.pdf eng