IntroStyle：利用扩散特征进行无需训练的内省式风格归因
IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features
AI总结：
本文提出无需训练的IntroStyle框架，仅利用扩散模型特征进行风格归因，并引入ArtSplit数据集，在WikiArt和DomainNet上大幅超越现有方法。
摘要：
文本到图像（T2I）模型最近获得了广泛采用。这引发了对保护知识产权的担忧，以及对防止生成特定艺术风格的机制日益增长的需求。现有的风格提取方法通常需要收集自定义数据集和训练专门的模型。然而，这耗费资源、耗时，并且对于实时应用往往不切实际。我们提出了一种新颖的、无需训练的框架来解决风格归因问题，仅使用扩散模型产生的特征，无需任何外部模块或重新训练。这被称为内省式风格归因（IntroStyle），并显示出在风格归因方面优于最先进模型的性能。我们还引入了一个名为艺术风格分割（ArtSplit）的合成数据集，以隔离艺术风格并评估细粒度风格归因性能。我们在WikiArt和DomainNet数据集上的实验结果表明，我们的方法对艺术风格的动态性质具有鲁棒性，大幅优于现有方法。
英文摘要：
Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles. Existing methods for style extraction typically necessitate the collection of custom datasets and the training of specialized models. This, however, is resource-intensive, time-consuming, and often impractical for real-time applications. We present a novel, training-free framework to solve the style attribution problem, using the features produced by a diffusion model alone, without any external modules or retraining. This is denoted as Introspective Style attribution (IntroStyle) and is shown to have superior performance to state-of-the-art models for style attribution. We also introduce a synthetic dataset of Artistic Style Split (ArtSplit) to isolate artistic style and evaluate fine-grained style attribution performance. Our experimental results on WikiArt and DomainNet datasets show that \ours is robust to the dynamic nature of artistic styles, outperforming existing methods by a wide margin.
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。
