解决扩散模型生成时的过自信问题，提升图像质量与多样性。
Enhancing Diffusion Model Guidance through Calibration and Regularization
- 用平滑期望校准误差优化分类器，提升预测可靠性。
- 新采样策略使图像FID达2.13，无需重训练扩散模型。
- 适合关注生成质量与稳定性的图像生成研究者。
分类器引导的扩散模型在条件图像生成中表现强劲，但在去噪初期常出现过自信预测，导致引导梯度消失。本文提出两项互补改进：首先，基于平滑期望校准误差（Smooth ECE）设计可微分校准目标，仅需少量微调即可提升分类器校准性，并显著改善弗雷切特初始距离（FID）；其次，开发无需重训练分类器的增强采样引导方法，包括批次级重加权的倾斜采样、自适应熵正则化采样以保持多样性，以及基于f-散度的新采样策略，在强化类别一致性引导的同时维持模式覆盖。在ImageNet 128x128上的实验表明，所提出的散度正则化引导方法使用ResNet-101分类器实现FID 2.13，优于现有方法，且无需重训练扩散模型。结果表明，有原则的校准与散度感知采样能有效提升分类器引导扩散模型的表现。
原文摘要 · Abstract (English)
Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper introduces two complementary contributions to address this issue. First, we propose a differentiable calibration objective based on the Smooth Expected Calibration Error (Smooth ECE), which improves classifier calibration with minimal fine-tuning and yields measurable improvements in Frechet Inception Distance (FID). Second, we develop enhanced sampling guidance methods that operate on off-the-shelf classifiers without requiring retraining. These include tilted sampling with batch-level reweighting, adaptive entropy-regularized sampling to preserve diversity, and a novel f-divergence-based sampling strategy that strengthens class-consistent guidance while maintaining mode coverage. Experiments on ImageNet 128x128 demonstrate that our divergence-regularized guidance achieves an FID of 2.13 using a ResNet-101 classifier, improving upon existing classifier-guided diffusion methods while requiring no diffusion model retraining. The results show that principled calibration and divergence-aware sampling provide practical and effective improvements for classifier-guided diffusion.
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。