论文标题
感知优先训练扩散模型
Perception Prioritized Training of Diffusion Models
论文作者
论文摘要
扩散模型通过优化相应的损失项的加权总和，即，将分数匹配损失损失来恢复噪声数据，该数据被不同级别的噪声损坏。在本文中，我们表明，恢复与某些噪声级别损坏的数据为模型学习丰富的视觉概念提供了适当的借口任务。我们建议通过重新设计目标函数的加权方案来将此类噪声水平优先于其他水平。我们表明，无论数据集，架构和采样策略如何，我们简单地重新设计加权方案都可以显着提高扩散模型的性能。
Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i.e., denoising score matching loss. In this paper, we show that restoring data corrupted with certain noise levels offers a proper pretext task for the model to learn rich visual concepts. We propose to prioritize such noise levels over other levels during training, by redesigning the weighting scheme of the objective function. We show that our simple redesign of the weighting scheme significantly improves the performance of diffusion models regardless of the datasets, architectures, and sampling strategies.
