Abstract
Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such supervision, often stemming from noisy, ambiguous, or incomplete labels, will cause condition mismatch and degrade generation quality. To address this challenge, we propose DMIS, a unified framework for training robust Diffusion Models from Imprecise Supervision, which is the first systematic study within diffusion models. Our framework is derived from likelihood maximization and decomposes the objective into generative and classification components: the generative component models imprecise-label distributions, while the classification component leverages a diffusion classifier to infer class-posterior probabilities, with its efficiency further improved by an optimized timestep sampling strategy. Extensive experiments on diverse forms of imprecise supervision, covering tasks of image generation, weakly supervised learning, and noisy dataset condensation demonstrate that DMIS consistently produces high-quality and class-discriminative samples.
Abstract (translated)
条件扩散模型在各种生成任务中最近取得了显著的成功，但它们的训练通常依赖于包含条件输入中不可避免地含有不精确信息的大规模数据集。这种监督往往来源于嘈杂、模糊或不完整的标签，会导致条件不匹配并降低生成质量。为了解决这一挑战，我们提出了DMIS（从含糊监督训练鲁棒扩散模型的统一框架），这是在扩散模型领域内的首个系统性研究。我们的框架源自于似然最大化，并将目标分解为生成和分类两个部分：生成部分建模模糊标签分布，而分类部分利用一个扩散分类器来推断类后验概率，并通过优化的时间步采样策略进一步提高其效率。在涵盖图像生成、弱监督学习及噪声数据集浓缩等各种形式的含糊监督上的广泛实验表明，DMIS能够持续产出高质量且具有类别区分能力的样本。
URL
https://arxiv.org/abs/2510.03016
