Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled distributions. Such synthetic datasets can augment the original training distribution when discriminative models, like semantic segmentation, are trained. However, this augmentation effect is limited since ControlNets tend to reproduce the original training distribution. This work introduces a method to utilize data from unlabeled domains to train ControlNets by introducing the concept of uncertainty into the control mechanism. The uncertainty indicates that a given image was not part of the training distribution of a downstream task, e.g., segmentation. Thus, two types of control are engaged in the final network: an uncertainty control from an unlabeled dataset and a semantic control from the labeled dataset. The resulting ControlNet allows us to create annotated data with high uncertainty from the target domain, i.e., synthetic data from the unlabeled distribution with labels. In our scenario, we consider retinal OCTs, where typically high-quality Spectralis images are available with given ground truth segmentations, enabling the training of segmentation networks. The recent development in Home-OCT devices, however, yields retinal OCTs with lower quality and a large domain shift, such that out-of-the-pocket segmentation networks cannot be applied for this type of data. Synthesizing annotated images from the Home-OCT domain using the proposed approach closes this gap and leads to significantly improved segmentation results without adding any further supervision. The advantage of uncertainty-guidance becomes obvious when compared to style transfer: it enables arbitrary domain shifts without any strict learning of an image style. This is also demonstrated in a traffic scene experiment.

翻译：生成模型是实现高质量图像数据可控生成的重要工具。诸如ControlNet之类的可控扩散模型使得创建带标签的数据分布成为可能。当训练判别式模型（如语义分割）时，此类合成数据集能够对原始训练分布进行增强。然而，由于ControlNet倾向于复现原始训练分布，这种增强效果受到限制。本文提出一种方法，通过将不确定性概念引入控制机制，利用未标注领域的数据来训练ControlNet。不确定性表明给定图像不属于下游任务（如分割）的训练分布。因此，最终网络采用两种控制机制：来自未标注数据集的不确定性控制和来自标注数据集的语义控制。由此得到的ControlNet使我们能够从目标领域创建具有高不确定性的标注数据，即从未标注分布中生成带标签的合成数据。在我们的研究场景中，我们以视网膜OCT图像为例，通常可获得带有真实分割标注的高质量Spectralis图像，用于训练分割网络。然而，家用OCT设备的最新发展产生了质量较低且存在显著领域偏移的视网膜OCT图像，使得现成的分割网络无法直接应用于此类数据。采用所提方法从家用OCT领域合成标注图像，能够弥合这一差距，在不引入额外监督的情况下显著提升分割效果。与风格迁移相比，不确定性引导的优势显而易见：它能够实现任意的领域偏移，而无需严格学习图像风格。这一优势在交通场景实验中也得到了验证。