Fair Attribute Classification through Latent Space De-biasing
Fair Attribute Classification through Latent Space De-biasing
复制标题
DOI：
10.1109/cvpr46437.2021.00918
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
V. V. Ramaswamy-V.;Sunnie S. Y. Kim;Olga Russakovsky
中科院分区：
文献类型：
--
作者：
V. V. Ramaswamy-V.;Sunnie S. Y. Kim;Olga Russakovsky
随着识别系统在现实世界中的大规模部署，视觉识别中的公平性正成为一个重要的讨论话题。从目标标签与受保护属性（例如，性别，种族）相关的数据中训练的模型可以学习并利用这些相关性。在这项工作中，我们引入了一种训练准确目标分类器的方法，同时减轻了源于这些相关性的偏差。我们使用gan生成逼真的图像，并在潜在空间中扰动这些图像，以生成每个保护属性平衡的训练数据。我们用这些生成的数据增强原始数据集，并通过经验证明，在增强数据集上训练的目标分类器显示出许多定量和定性的好处。我们对CelebA数据集中的多个目标标签和受保护属性进行了全面的评估，并对空间中的现有文献进行了深入的分析和比较。代码可以在https://github.com/princetonvisualai/gan-debiasing上找到。
Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes (e.g., gender, race) are known to learn and exploit those correlations. In this work, we introduce a method for training accurate target classifiers while mitigating biases that stem from these correlations. We use GANs to generate realistic-looking images, and perturb these images in the underlying latent space to generate training data that is balanced for each protected attribute. We augment the original dataset with this generated data, and empirically demonstrate that target classifiers trained on the augmented dataset exhibit a number of both quantitative and qualitative benefits. We conduct a thorough evaluation across multiple target labels and protected attributes in the CelebA dataset, and provide an in-depth analysis and comparison to existing literature in the space. Code can be found at https://github.com/princetonvisualai/gan-debiasing.