Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition mismatch and quality degradation of generated data. This paper proposes Transition-aware weighted Denoising Score Matching (TDSM) for training conditional diffusion models with noisy labels, which is the first study in the line of diffusion models. The TDSM objective contains a weighted sum of score networks, incorporating instance-wise and time-dependent label transition probabilities. We introduce a transition-aware weight estimator, which leverages a time-dependent noisy-label classifier distinctively customized to the diffusion process. Through experiments across various datasets and noisy label settings, TDSM improves the quality of generated samples aligned with given conditions. Furthermore, our method improves generation performance even on prevalent benchmark datasets, which implies the potential noisy labels and their risk of generative model learning. Finally, we show the improved performance of TDSM on top of conventional noisy label corrections, which empirically proving its contribution as a part of label-noise robust generative models. Our code is available at: https://github.com/byeonghu-na/tdsm.

翻译：条件扩散模型在各种生成任务中展现出卓越性能，但其训练需要大规模数据集，而这些数据集的输入中常包含噪声（即噪声标签）。这种噪声会导致条件不匹配和生成数据质量下降。本文提出针对扩散模型的首项研究——过渡感知加权去噪分数匹配（TDSM），用于训练带有噪声标签的条件扩散模型。TDSM目标函数包含分数网络的加权和，并融入实例依赖与时间依赖的标签转移概率。我们引入过渡感知权重估计器，该估计器利用专为扩散过程定制的时变噪声标签分类器。通过跨不同数据集和噪声标签设置的实验，TDSM提升了与给定条件对齐的生成样本质量。此外，即使在常见基准数据集上，我们的方法也改善了生成性能，这暗示了潜在噪声标签及其对生成模型学习的风险。最后，我们展示了TDSM在传统噪声标签修正基础上的性能提升，实证证明了其作为标签噪声鲁棒生成模型组成部分的贡献。我们的代码开源在：https://github.com/byeonghu-na/tdsm。