ReFACT：通过编辑文本编码器更新文本到图像模型
ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
AI总结：
本文提出ReFACT方法，通过仅编辑文本编码器中特定层的少量权重来更新文本到图像模型中的事实关联，无需用户输入或重新训练，并在泛化与保持性能上优于现有方法。
摘要：
我们的世界正经历前所未有的技术、全球和社会政治变革，这对文本到图像生成模型构成了重大挑战。这些模型在其参数中编码的事实关联可能很快过时，从而降低其对最终用户的效用。为此，我们提出ReFACT，这是一种在文本到图像模型中编辑事实关联的新方法，无需依赖最终用户的显式输入或昂贵的重新训练。ReFACT更新文本编码器中特定层的权重，仅修改模型参数的一小部分，而保持模型其余部分不受影响。我们在现有基准以及一个新整理的数据集上对ReFACT进行了实证评估。与其他方法相比，ReFACT在相关概念的泛化和无关概念的保持方面均取得了更优的性能。此外，ReFACT保持了图像生成质量，使其成为更新和纠正文本到图像模型中事实信息的实用工具。
英文摘要：
Our world is marked by unprecedented technological, global, and socio-political transformations, posing a significant challenge to text-to-image generative models. These models encode factual associations within their parameters that can quickly become outdated, diminishing their utility for end-users. To that end, we introduce ReFACT, a novel approach for editing factual associations in text-to-image models without relaying on explicit input from end-users or costly re-training. ReFACT updates the weights of a specific layer in the text encoder, modifying only a tiny portion of the model's parameters and leaving the rest of the model unaffected. We empirically evaluate ReFACT on an existing benchmark, alongside a newly curated dataset. Compared to other methods, ReFACT achieves superior performance in both generalization to related concepts and preservation of unrelated concepts. Furthermore, ReFACT maintains image generation quality, making it a practical tool for updating and correcting factual information in text-to-image models.
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。
