让扩散模型在极噪声条件下仍能生成准确结果
Robust Learning of Diffusion Models with Extremely Noisy Conditions
- 用伪条件替代噪声条件，逐步优化伪条件
- 在高噪声下图像和策略生成效果优于现有方法
- 适合处理标签错误、观测不准等实际噪声场景
条件扩散模型通过引入外部条件实现生成可控性，但在条件噪声过高时性能显著下降，如图像生成中的标签损坏或控制策略生成中的不可靠观测。本文提出一种鲁棒学习框架，应对极端噪声条件。实验表明，现有抗噪方法在高噪声下失效。为此，我们提出学习伪条件作为干净条件的替代，并通过时间集成技术逐步优化伪条件。此外，设计了反向时间扩散条件（RDC）技术，将伪条件反向扩散以增强记忆效应，进一步促进伪条件的优化。在类别条件图像生成和视觉运动策略生成任务上，该方法在多种噪声水平下均达到当前最优表现。
原文摘要 · Abstract (English)
Conditional diffusion models have the generative controllability by incorporating external conditions. However, their performance significantly degrades with noisy conditions, such as corrupted labels in the image generation or unreliable observations or states in the control policy generation. This paper introduces a robust learning framework to address extremely noisy conditions in conditional diffusion models. We empirically demonstrate that existing noise-robust methods fail when the noise level is high. To overcome this, we propose learning pseudo conditions as surrogates for clean conditions and refining pseudo ones progressively via the technique of temporal ensembling. Additionally, we develop a Reverse-time Diffusion Condition (RDC) technique, which diffuses pseudo conditions to reinforce the memorization effect and further facilitate the refinement of the pseudo conditions. Experimentally, our approach achieves state-of-the-art performance across a range of noise levels on both class-conditional image generation and visuomotor policy generation tasks.The code can be accessible via the project page https://robustdiffusionpolicy.github.io
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。