Despite the high-quality results of text-to-image generation, stereotypical biases have been spotted in their generated contents, compromising the fairness of generative models. In this work, we propose to learn adaptive inclusive tokens to shift the attribute distribution of the final generative outputs. Unlike existing de-biasing approaches, our method requires neither explicit attribute specification nor prior knowledge of the bias distribution. Specifically, the core of our method is a lightweight adaptive mapping network, which can customize the inclusive tokens for the concepts to be de-biased, making the tokens generalizable to unseen concepts regardless of their original bias distributions. This is achieved by tuning the adaptive mapping network with a handful of balanced and inclusive samples using an anchor loss. Experimental results demonstrate that our method outperforms previous bias mitigation methods without attribute specification while preserving the alignment between generative results and text descriptions. Moreover, our method achieves comparable performance to models that require specific attributes or editing directions for generation. Extensive experiments showcase the effectiveness of our adaptive inclusive tokens in mitigating stereotypical bias in text-to-image generation. The code will be available at https://github.com/itsmag11/AITTI.

翻译：尽管文本到图像生成模型已能产生高质量结果，但其生成内容中仍存在刻板偏见，损害了生成模型的公平性。本研究提出通过学习自适应包容性标记来调整最终生成结果的属性分布。与现有去偏见方法不同，我们的方法既不需要显式指定属性，也不要求预先了解偏见分布。具体而言，本方法的核心是一个轻量级自适应映射网络，该网络可为待去偏见的概念定制包容性标记，使这些标记能够泛化到未见过的概念，而不受其原始偏见分布的影响。这是通过使用锚点损失函数，基于少量平衡且包容的样本对自适应映射网络进行微调实现的。实验结果表明，本方法在无需指定属性的情况下优于先前的偏见缓解方法，同时保持了生成结果与文本描述之间的对齐性。此外，本方法取得了与需要特定属性或编辑方向进行生成的模型相当的性能。大量实验证明了我们的自适应包容性标记在缓解文本到图像生成中的刻板偏见方面的有效性。代码将在 https://github.com/itsmag11/AITTI 发布。