PulseAugur
中
实时 12:54:21
English(EN) Class-frequency Guided Noise Schedule for Diffusion Models

新的噪声调度和EM算法提升扩散模型性能

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员开发了一种新的扩散模型噪声调度方法，称为类别频率引导（CFRG），以提高生成质量，特别是在类别不平衡数据集中的低频类别。该方法解决了低密度区域导致分数估计不准确以及高频类别主导生成过程的问题。在类别不平衡数据集（如CIFAR-100-LT和ImageNet-LT）上的图像生成、分类和文本到图像任务的实验表明，与现有方法相比有显著改进。另外，另一篇研究论文介绍了EMDiffusion，一种从损坏观测中训练扩散模型的期望最大化算法，在图像修复、去噪和去模糊等计算成像任务中取得了最先进的结果。 AI

影响 扩散模型训练和噪声调度的这些进展可能带来更高质量的图像生成以及在各种计算机视觉任务中性能的提升。

排序理由 该集群包含两篇在arXiv上发表的独立研究论文，详细介绍了改进扩散模型的新颖方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的噪声调度和EM算法提升扩散模型性能

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang ·

    Class-frequency Guided Noise Schedule for Diffusion Models

    arXiv:2606.27696v1 Announce Type: cross Abstract: In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models. For score-based generative models, low-density regions often lead to inaccurately esti…

  2. arXiv cs.LG TIER_1 English(EN) · Hanwang Zhang ·

    Class-frequency Guided Noise Schedule for Diffusion Models

    In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models. For score-based generative models, low-density regions often lead to inaccurately estimated scores, thereby compromising the generation …

  3. arXiv cs.CV TIER_1 English(EN) · Weimin Bai, Yifei Wang, Wenzheng Chen, He Sun ·

    An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

    arXiv:2407.01014v2 Announce Type: replace Abstract: Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. …

相关实体

相关话题