无分类器引导调度的对抗学习

中文摘要 AI 辅助

现代文本到图像的扩散模型依赖无分类器引导（Classifier-Free Guidance，CFG）来实现高图像保真度和文本对齐。然而，CFG通常在所有时间步、样本和条件下应用静态全局尺度，这种选择通常次优且会引入伪影，因为不同状态可能受益于不同水平的引导。虽然时变调度已知可提升质量，但手动设计它们并非易事且依赖于应用。本文中，我们将引导调度学习为扩散时间、条件和当前噪声样本的函数，以更好地使采样图像与文本提示对齐。我们将此问题表述为密度比估计问题：训练判别器以估计真实和引导边际分布之间的时间相关对数密度比，同时轻量生成器网络预测最优的、状态相关的引导尺度。在文本到图像生成基准上的实验表明，我们的方法在启发式CFG调度和现有动态引导学习方法上表现更优。

英文摘要

Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scale across all timesteps, samples, and conditions -- a choice that is generally suboptimal and can introduce artifacts, as different states may benefit from different levels of guidance. While time-varying schedules are known to improve quality, designing them by hand is non-trivial and application-dependent. In this paper, we learn the guidance schedule as a function of diffusion time, conditioning and the current noisy sample, in order to better align sampled images with the text prompt. We frame this as a density ratio estimation problem: a discriminator is trained to estimate the time-dependent log-density ratio between the true and guided marginal distributions, while a lightweight generator network predicts the optimal, state-dependent guidance scale. Empirically, our approach outperforms both heuristic CFG schedules and prior methods for learning dynamic guidance on text-to-image generation benchmarks.

发表机构

• Google（谷歌公司）
• Google DeepMind（谷歌DeepMind）
• Gatsby UCL（盖茨比伦敦大学学院）

机构由 AI 辅助整理，请以论文原文为准。