迈向互联网规模文本到图像扩散模型的安全自蒸馏
Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models
AI总结：
针对文本到图像扩散模型可能生成有害或版权内容的问题，本文提出 SDD 自蒸馏方法，使目标概念条件噪声估计逼近无条件估计，可在保持图像质量的同时更有效地移除多个概念。
摘要：
大规模图像生成模型借助互联网上可用的海量数据实现了令人瞩目的质量，但也引发了社会担忧：这些模型可能生成有害或受版权保护的内容。偏见和有害性在整个训练过程中产生，并且难以彻底消除，已成为安全部署这些模型的重大障碍。在本文中，我们提出一种名为 SDD 的方法，用于防止文本到图像扩散模型生成有问题的内容。我们对扩散模型进行自蒸馏，引导以目标移除概念为条件的噪声估计与无条件噪声估计相匹配。与以往方法相比，我们的方法在不降低整体图像质量的情况下，从生成图像中消除了比例高得多的有害内容。此外，我们的方法允许一次移除多个概念，而以往工作仅限于一次移除单个概念。
英文摘要：
Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content. The biases and harmfulness arise throughout the entire training process and are hard to completely remove, which have become significant hurdles to the safe deployment of these models. In this paper, we propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. We self-distill the diffusion model to guide the noise estimate conditioned on the target removal concept to match the unconditional one. Compared to the previous methods, our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality. Furthermore, our method allows the removal of multiple concepts at once, whereas previous works are limited to removing a single concept at a time.
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。
