用少量干净数据+噪声数据训练扩散模型，实现高效生成且避免版权问题。
Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
- 先用少量干净数据预训练，再结合随机正反向去卷积方法处理噪声数据。
- 仅用4%干净图像即达CIFAR-10上FID 6.31，10%时降至3.58。
- 理论证明可学习真实数据分布，适合关注版权合规的生成模型研究者。
近期基于扩散的生成模型在大规模数据集上表现卓越，但引发记忆与版权争议。一种解决方案是仅使用带噪声的数据进行训练，确保模型不接触原始内容。然而，从去卷积理论看，虽理论上可行，但因需大量样本，实际学习几乎不可行。为此，我们提出先用少量干净数据预训练以引导去卷积过程，并结合随机正反向去卷积（SFBD）方法，在仅4%干净图像下于CIFAR-10上达到FID 6.31（10%时为3.58）。我们还提供了理论保证，证明SFBD能学习真实数据分布。实验验证了该方法的有效性，强调了有限干净数据或相似数据集预训练的价值。
原文摘要 · Abstract (English)
Recent diffusion-based generative models achieve remarkable results by training on massive datasets, yet this practice raises concerns about memorization and copyright infringement. A proposed remedy is to train exclusively on noisy data with potential copyright issues, ensuring the model never observes original content. However, through the lens of deconvolution theory, we show that although it is theoretically feasible to learn the data distribution from noisy samples, the practical challenge of collecting sufficient samples makes successful learning nearly unattainable. To overcome this limitation, we propose to pretrain the model with a small fraction of clean data to guide the deconvolution process. Combined with our Stochastic Forward--Backward Deconvolution (SFBD) method, we attain FID 6.31 on CIFAR-10 with just 4% clean images (and 3.58 with 10%). We also provide theoretical guarantees that SFBD learns the true data distribution. These results underscore the value of limited clean pretraining, or pretraining on similar datasets. Empirical studies further validate and enrich our findings.
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。