自发现可解释扩散潜在方向以实现负责任的文本到图像生成
Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
AI总结：
本文提出一种自监督方法，在扩散模型潜在空间中自动发现任意概念的可解释方向，并利用这些方向缓解不当生成，实现公平、安全且负责任的文本到图像生成。
摘要：
基于扩散的模型因其卓越的图像生成能力而在文本到图像生成中获得了显著普及。这些模型的一个风险是可能生成不当内容，例如有偏见或有害的图像。然而，从扩散模型内部表示的角度来看，生成此类不良内容的根本原因仍不清楚。先前的工作将扩散模型可解释潜在空间中的向量解释为语义概念。然而，现有方法无法为任意概念发现方向，例如与不当概念相关的方向。在这项工作中，我们提出了一种新颖的自监督方法，用于为给定概念找到可解释的潜在方向。利用所发现的向量，我们进一步提出了一种简单的方法来缓解不当生成。我们进行了大量实验以验证缓解方法的有效性，即公平生成、安全生成和负责任的文本增强生成。项目页面：\url{https://interpretdiffusion.github.io}。
英文摘要：
Diffusion-based models have gained significant popularity for text-to-image generation due to their exceptional image-generation capabilities. A risk with these models is the potential generation of inappropriate content, such as biased or harmful images. However, the underlying reasons for generating such undesired content from the perspective of the diffusion model's internal representation remain unclear. Previous work interprets vectors in an interpretable latent space of diffusion models as semantic concepts. However, existing approaches cannot discover directions for arbitrary concepts, such as those related to inappropriate concepts. In this work, we propose a novel self-supervised approach to find interpretable latent directions for a given concept. With the discovered vectors, we further propose a simple approach to mitigate inappropriate generation. Extensive experiments have been conducted to verify the effectiveness of our mitigation approach, namely, for fair generation, safe generation, and responsible text-enhancing generation. Project page: \url{https://interpretdiffusion.github.io}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
