不依赖梯度或重训练，用图像相似性评估数据对生成结果的影响。
Nonparametric Data Attribution for Diffusion Models
- 基于图像块级相似性计算数据影响，无需模型梯度或重训练。
- 在多个数据集上性能接近基于梯度的方法，显著优于现有非参数基线。
- 适用于闭源或大规模模型，输出空间可解释的归因图谱。
生成模型的数据归因旨在量化单个训练样本对模型输出的影响。现有扩散模型的归因方法通常需要模型梯度或重新训练，限制了其在私有或大规模场景下的应用。本文提出一种完全基于数据的非参数归因方法，通过生成图像与训练图像间的块级相似性来衡量影响。该方法基于最优得分函数的解析形式，自然拓展至多尺度表示，并通过卷积加速保持计算高效。除生成空间可解释的归因外，框架还揭示了训练数据与输出之间的内在关联模式，且不依赖特定模型。实验表明，该方法在多个基准上表现优异，性能接近基于梯度的方法，显著优于现有非参数基线。代码已开源：https://github.com/sail-sg/NDA。
原文摘要 · Abstract (English)
Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, limiting their applicability in proprietary or large-scale settings. We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images. Our approach is grounded in the analytical form of the optimal score function and naturally extends to multiscale representations, while remaining computationally efficient through convolution-based acceleration. In addition to producing spatially interpretable attributions, our framework uncovers patterns that reflect intrinsic relationships between training data and outputs, independent of any specific model. Experiments demonstrate that our method achieves strong attribution performance, closely matching gradient-based approaches and substantially outperforming existing nonparametric baselines. Code is available at https://github.com/sail-sg/NDA.
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。