无需训练，仅用扩散模型特征实现精准风格归属识别
IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features
- 利用扩散模型自身特征实现风格归属，无需额外训练
- 在WikiArt和DomainNet上显著优于现有方法
- 专为细粒度风格识别设计的合成数据集支持评估
文本到图像（T2I）模型已广泛应用，引发对知识产权保护的关注，亟需防止特定艺术风格生成的机制。现有风格提取方法通常依赖自定义数据集和专用模型训练，成本高且难以实时应用。本文提出无需训练的全新框架IntroStyle，仅使用扩散模型内部特征完成风格归属，称为内省式风格归属。我们还构建了人工风格分割数据集ArtSplit，用于分离艺术风格并评估细粒度归属性能。在WikiArt和DomainNet上的实验表明，该方法对艺术风格的动态变化具有鲁棒性，性能大幅超越现有最优模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。