Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to potential biases against underrepresented minorities if left uncontrolled. In this work, we first formalize the problem of minority inclusion as one of data coverage, and then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. The experiments show that our method outperforms the existing state-of-the-art methods in terms of data coverage on both seen and unseen data. We develop an extension that allows explicit control over the minority subgroups that the model should ensure to include, and validate its effectiveness at little compromise from the overall performance on the entire dataset. Code, models, and supplemental videos are available at GitHub.

中文翻译：

---

包容性 GAN：提高生成模型中的数据和少数群体覆盖率

生成对抗网络 (GAN) 在生成逼真图像方面取得了快速进展。然而，在亚组之间公平分配他们的建模能力受到的关注较少，如果不受控制，这可能导致对代表性不足的少数群体的潜在偏见。在这项工作中，我们首先将少数群体包含问题正式化为数据覆盖率之一，然后建议通过将对抗性训练与重建生成相协调来提高数据覆盖率。实验表明，我们的方法在可见和不可见数据的数据覆盖率方面优于现有的最先进方法。我们开发了一个扩展，允许对模型应确保包括的少数子组进行显式控制，并在不影响整个数据集的整体性能的情况下验证其有效性。GitHub 上提供了代码、模型和补充视频。