无需训练即可实现精准条件生成，提升采样质量。
TFTF: Training-Free Targeted Flow for Conditional Sampling
- 基于重要性采样与SMC重采样，避免高维权重退化。
- 引入可调噪声的随机流，使样本轨迹更分散。
- 适用于图像生成等高维多模态任务，效果优于现有方法。
我们提出一种无需训练的流匹配模型条件采样方法，基于重要性采样。由于朴素的重要性采样在高维场景中易出现权重退化，我们在生成过程的中间阶段引入序贯蒙特卡洛（SMC）中的重采样技术进行修正。为促使生成样本沿不同轨迹发散，我们推导出一种可调节噪声强度的随机流，替代中间阶段的确定性流。该框架无需额外训练，同时具备渐近准确性的理论保证。实验表明，该方法在MNIST和CIFAR-10上的条件采样任务中显著优于现有方法。进一步在CelebA-HQ上的人脸文本生成实验中，验证了其在更高维、多模态场景下的适用性。
原文摘要 · Abstract (English)
We propose a training-free conditional sampling method for flow matching models based on importance sampling. Because a naïve application of importance sampling suffers from weight degeneracy in high-dimensional settings, we modify and incorporate a resampling technique in sequential Monte Carlo (SMC) during intermediate stages of the generation process. To encourage generated samples to diverge along distinct trajectories, we derive a stochastic flow with adjustable noise strength to replace the deterministic flow at the intermediate stage. Our framework requires no additional training, while providing theoretical guarantees of asymptotic accuracy. Experimentally, our method significantly outperforms existing approaches on conditional sampling tasks for MNIST and CIFAR-10. We further demonstrate the applicability of our approach in higher-dimensional, multimodal settings through text-to-image generation experiments on CelebA-HQ.
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。