通过切换专家模型，同时提升图像质量和数据似然。
Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts
- 在高噪声时用结构专家，低噪声时切换到统计专家。
- 在CIFAR-10和ImageNet32上同时提升似然与图像质量。
- 无需重训练，仅需选择切换点，适合快速部署。
图像生成的扩散模型常面临感知质量与数据似然之间的权衡：强调高噪声阶段去噪的训练会生成更真实图像但似然较低，而侧重似然的训练则过度关注低噪声阶段，损害视觉质量。本文提出一种简单即插即用的采样方法，通过在去噪轨迹中切换两个预训练扩散专家实现融合：在高噪声水平使用图像质量专家塑造全局结构，低噪声阶段切换至似然专家细化像素统计。该方法无需重新训练或微调，仅需选择中间切换步骤。在CIFAR-10和ImageNet32上，融合模型始终优于或等同于单个专家，同时提升或保持了似然与样本质量。结果表明，基于噪声水平的专家切换是打破扩散模型似然-质量权衡的有效策略。
原文摘要 · Abstract (English)
Diffusion models for image generation often exhibit a trade-off between perceptual sample quality and data likelihood: training objectives emphasizing high-noise denoising steps yield realistic images but poor likelihoods, whereas likelihood-oriented training overweights low-noise steps and harms visual fidelity. We introduce a simple plug-and-play sampling method that combines two pretrained diffusion experts by switching between them along the denoising trajectory. Specifically, we apply an image-quality expert at high noise levels to shape global structure, then switch to a likelihood expert at low noise levels to refine pixel statistics. The approach requires no retraining or fine-tuning -- only the choice of an intermediate switching step. On CIFAR-10 and ImageNet32, the merged model consistently matches or outperforms its base components, improving or preserving both likelihood and sample quality relative to each expert alone. These results demonstrate that expert switching across noise levels is an effective way to break the likelihood-quality trade-off in image diffusion models.
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。