通过频率控制噪声，让扩散模型更聚焦数据关键特征。
Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
- 用频域噪声操作构建模型先验偏好
- 相比标准扩散，生成性能显著提升
- 适合需要抑制特定频率信息的任务
扩散概率模型（DPMs）在众多生成任务中表现卓越。本文旨在通过训练与采样过程中的设计，为扩散模型引入结构化先验，以更好匹配目标数据分布。针对具有拓扑结构的数据，我们提出一种基于频率的加噪算子，可有目的地操控和设定这些先验。实验表明，合理设计前向加噪过程能使模型聚焦于分布的特定方面进行学习。不同数据集需不同先验，而适当的频率控制能带来优于标准扩散模型的生成性能。此外，我们展示了在学习过程中忽略特定频率信息的可能性，并在严重噪声破坏后的图像恢复任务中验证：训练模型可在去除高频干扰后重建原始分布。
原文摘要 · Abstract (English)
Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks. In this work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. For topologically structured data, we devise a frequency-based noising operator to purposefully manipulate, and set, these inductive biases. We first show that appropriate manipulations of the noising forward process can lead DPMs to focus on particular aspects of the distribution to learn. We show that different datasets necessitate different inductive biases, and that appropriate frequency-based noise control induces increased generative performance compared to standard diffusion. Finally, we demonstrate the possibility of ignoring information at particular frequencies while learning. We show this in an image corruption and recovery task, where we train a DPM to recover the original target distribution after severe noise corruption.
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。